{"old": "/home/jenkins/agent/workspace/multiarch/src-openeuler/aarch64/pytorch/old_rpms/", "new": "/home/jenkins/agent/workspace/multiarch/src-openeuler/aarch64/pytorch/new_rpms/", "compare_result": "not pass", "compare_details": {"same": {"same_details": {"old": [], "new": []}, "same_num": 0}, "diff": {"diff_details": {"python3-pytorch": {"name": {"old": "python3-pytorch-2.1.2-5.oe2403sp4.aarch64.rpm", "new": "python3-pytorch-2.7.0-1.oe2403sp4.aarch64.rpm"}, "RPM Level": "level4", "rpm requires": {"diff": {"old": ["python3.11dist(sympy)", "python3.11dist(typing-extensions)"], "new": ["python3.11dist(sympy) >= 1.13.3", "python3.11dist(typing-extensions) >= 4.10"]}}, "rpm provides": {"more": ["libaoti_custom_ops.so()(64bit)"]}, "rpm files": {"less": ["/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/graph_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/blockpartition.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/copy.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/upgrade.py", "/usr/lib64/python3.11/site-packages/torch/test/c10_either_test", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_propagate_annotation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_exporter_states.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/__pycache__/fully_shard.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/log_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/checkpoint.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/comm_tensor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/__pycache__/end_to_end.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/sharding_prop.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/_collective_utils.py", "/usr/lib64/python3.11/site-packages/torch/optim/radam.pyi", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/optests/__pycache__/compile_check.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipeline/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/op_schema.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/basic_strategy.py", "/usr/lib64/python3.11/site-packages/torch/optim/asgd.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/op_schema.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/skippable.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/pipeline.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/worker.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipeline", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/dependency.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/optests/__pycache__/compile_check.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/dependency.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/comm_tensor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/__pycache__/blas_compare.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/redistribute.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/parallel_mode.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/profile.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/pipe.py", "/usr/lib64/python3.11/site-packages/torch/test/variant_test", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_exporter_states.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/coordinate_descent_tuner.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/config_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/device_mesh.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_foreach.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/constraints.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/__pycache__/flat_param.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cuda_properties.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/dependency.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/tensor_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/lbfgs.pyi", "/usr/lib64/python3.11/site-packages/torch/include/c10/core/impl/cow", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/namespace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/math_ops.py", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/__pycache__/blas_compare.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/__pycache__/op_validation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/matrix_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_heuristics.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/common_rules.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/distribute.py", "/usr/lib64/python3.11/site-packages/torch/optim/rprop.pyi", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipeline/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_export/exported_program.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/graph_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/namespace.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/tracker.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/graph_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/config.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/common_rules.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_helpers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/view_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/phony.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_deprecation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/checkpoint.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/embedding_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_foreach.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/pipe.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_helpers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/skippable.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/skipfiles.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/op_coverage.py", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/__pycache__/end_to_end.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/codegen/__pycache__/random_topo_test.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/nadam.pyi", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cuda_trace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/matrix_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/random_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cuda_trace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/pipeline.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/__pycache__/op_validation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/__pycache__/pipe_with_ddp_test.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fully_shard.py", "/usr/lib64/python3.11/site-packages/torch/optim/adamax.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/log_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/adagrad.pyi", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/end_to_end.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/log_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/iter_graph_module.py", "/usr/lib64/python3.11/site-packages/torch/utils/_cuda_trace.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/matrix_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/iter_graph_module.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/_dynamo_utils.py", "/usr/lib64/python3.11/site-packages/torch/optim/rmsprop.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/batchnorm.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/constraints.py", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_exporter_states.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_collective_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/view_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_sym_size_ops_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/unpack_mixed_mm.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/control_flow_opinfo_db.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/random_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/view_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cuda_properties.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/portal.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/experimental_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/upgrade.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/profile.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/benchmark/examples/blas_compare.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/microbatch.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_collective_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/UCCForNCCL.hpp", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/distribute.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/portal.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/stream.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipe_with_ddp_test.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_heuristics.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_dynamo_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops", "/usr/lib64/python3.11/site-packages/torch/_export/passes/replace_sym_size_ops_pass.py", "/usr/lib64/python3.11/site-packages/torch/optim/__init__.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/batch_dim_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/swa_utils.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/math_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/layout.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/tensor_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/phony.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/data_parallel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/redistribute.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/common_rules.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/stream.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/dispatch.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/checkpoint.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/optests/compile_check.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/allowed_functions.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/random.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/device_mesh.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/sharding_prop.py", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_deprecation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/skipfiles.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/pipe.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/data_parallel.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/copy.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug", "/usr/lib64/python3.11/site-packages/torch/_inductor/coordinate_descent_tuner.py", "/usr/lib64/python3.11/site-packages/torch/optim/lr_scheduler.pyi", "/usr/lib64/python3.11/site-packages/functorch/experimental/_map.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/allowed_functions.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/api.py", "/usr/lib64/python3.11/site-packages/torch/utils/data/_utils/__pycache__/serialization.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_custom_op/__pycache__/functional.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/basic_strategy.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_beartype.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/device_mesh.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__init__.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/exporter.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/tensorboard/__pycache__/_caffe2_graph.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/data_parallel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/skipfiles.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/config_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/config.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/api.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/ProcessGroupRoundRobin.hpp", "/usr/lib64/python3.11/site-packages/torch/fx/__init__.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/random.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/triton_helpers.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/unpack_mixed_mm.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/blockpartition.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/control_flow_opinfo_db.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/__pycache__/fully_shard.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/flat_param.py", "/usr/lib64/python3.11/site-packages/torch/utils/tensorboard/__pycache__/_caffe2_graph.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/allowed_functions.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/constraints.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/blockpartition.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/random_ops.py", "/usr/lib64/python3.11/site-packages/torch/test/c10_context_test", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/__pycache__/pipe_with_ddp_test.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/partial_lower.py", "/usr/lib64/python3.11/site-packages/functorch/experimental/__pycache__/_map.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/basic_strategy.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/parallel_mode.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/graph_optimization.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/upgrade.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/layout.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/sharding_prop.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipeline/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/iter_graph_module.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/adam.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/redistribute.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/config.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/op_validation.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__init__.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_beartype.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/phony.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/tensorboard/_caffe2_graph.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_dynamo_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/experimental_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__pycache__/op_coverage.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/pipeline/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/distribute.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/pointwise_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/layout.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/dispatch.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/microbatch.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/partial_lower.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/coordinate_descent_tuner.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/portal.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/experimental_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/graph_optimization.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/pipeline.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/comm_tensor.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/batch_dim_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/skippable.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/adamw.pyi", "/usr/lib64/python3.11/site-packages/torch/optim/sparse_adam.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/math_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/aot_inductor_interface.cpp", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/batchnorm.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/data/_utils/__pycache__/serialization.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/pointwise_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__pycache__/namespace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/api.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/__pycache__/_view_with_dim_change.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_propagate_annotation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/__pycache__/_view_with_dim_change.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/exported_program.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/cuda/ROCmLoops.cuh", "/usr/lib64/python3.11/site-packages/torch/_custom_op/__pycache__/functional.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/graph_optimization.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/__pycache__/flat_param.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_deprecation.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/triton_heuristics.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/_propagate_annotation.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/batchnorm.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/tensor_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/copy.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/skip/__init__.py", "/usr/lib64/python3.11/site-packages/torch/optim/sgd.pyi", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/exporter.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/worker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/codegen/random_topo_test.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/stream.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/codegen/__pycache__/random_topo_test.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/microbatch.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/pointwise_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/data/_utils/serialization.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/parallel_mode.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/unpack_mixed_mm.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/partial_lower.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/dispatch.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/profile.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/control_flow_opinfo_db.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/_beartype.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/gm_transformation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/cuda_properties.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__", "/usr/lib64/python3.11/site-packages/torch/optim/adadelta.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/_view_with_dim_change.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/batch_dim_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__/gm_transformation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/_balance/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/__pycache__/random.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_sym_size_ops_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/sync/__pycache__/worker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/embedding_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/debug/__pycache__/op_coverage.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_spmd/gm_transformation.py", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/exported_program.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/triton_foreach.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/op_schema.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipeline/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/config_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/functorch/experimental/__pycache__/_map.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tensor/ops/__pycache__/embedding_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_custom_op/functional.py"], "more": ["/usr/lib64/python3.11/site-packages/torch/_C/_aoti.pyi", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/state_dict.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/utils/__pycache__/matcher_with_name_node_map_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__main__.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/schemas.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/deterministic.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_14.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/bmm_pattern.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/reinplace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_errors.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_building.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/__pycache__/control_plane.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/duplicate_dq_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_init.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_2.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/numbers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/converter.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__pycache__/fallback_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/trace_rules.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/cpu/vec/vec128", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cuda_combined_scheduling.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/structured.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/timer/__pycache__/debug_info_logging.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_extension.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/cuda/PhiloxUtils.cuh", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_conv_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_schemas.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/runtime_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/trace_rules.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mock_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_tensors.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/runtime_wrappers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_6.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/strict_mode.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/custom_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/hints.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_core.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/aoti_call_delegate.py", "/usr/lib64/python3.11/site-packages/torch/mtia/memory.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/remove_runtime_assertions.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/_MMRankingA100.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/graph_signature.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/__pycache__/control_plane.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/_tensorify_python_scalars.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/code_context.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/random.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/functools.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/simd_kernel_features.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_kernel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_sharding_prop.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/autograd_cache.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/port_metadata_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/repro/aoti.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/replace_quantized_ops_with_standard_ops_pass.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/__main__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/stateful.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comm_lowering.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/functools.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/tools.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/fuzzer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/symbolic_opset19.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_17.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_with_hop_pass_util.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/pytree.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_attention.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/distributed.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/bmm_pattern.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/ilp_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/flex_attention.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/script_object.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_op_schema.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/triton_kernel_wrap.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/decomp_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_16.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_executor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_dispatch.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/graph_deduplication.py", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/DMAConnectivity.hpp", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/graph_signature.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_runner", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/handlers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_16.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_exporter_legacy.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/mod_tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_ordered_set.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__pycache__/_paged_attention.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/tunable.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/nnpack/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/_gpu_trace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/stage.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_serialization.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/rendezvous/__pycache__/_etcd_stub.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/freezing_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib", "/usr/lib64/python3.11/site-packages/torch/amp/__pycache__/grad_scaler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/collect_metadata_analysis.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module3.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/accelerator/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__init__.py", "/usr/lib64/python3.11/site-packages/torch/backends/cusparselt/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/version.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/logging_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_appending_byte_serializer.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_universal_gemm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu", "/usr/lib64/python3.11/site-packages/torch/include/ATen/cuda/tunable", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_combo_kernel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_verification.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/halide_helpers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_torch", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/nested_tensor.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_state.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__pycache__", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/Backoff.hpp", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_param_group.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/aoti_eager.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__pycache__/config.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/run_const_graph.py", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/_structures.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_tensor_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/autoheuristic_utils.py", "/usr/lib64/python3.11/site-packages/torch/export/passes/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_flat_param.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_pointwise_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/builtins.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_embedding_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_tree_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module3.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_tensors.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_set_grad_with_hop_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/schema.yaml", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/invoke_subgraph.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/packaged/autograd/gen_view_funcs.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/torchbind_impls.py", "/usr/lib64/python3.11/site-packages/torch/utils/_triton.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/sdpa.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/_node_metadata_hook.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_environment.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_checkpointable.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_reporting.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/mps.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/hop.py", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_graph_pickler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_triton.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_deduplication.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/transformers", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/jit_compile_runtime_wrappers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_11.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_5.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_template_kernel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/subclass_parametrization.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/constant_folding.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/torchbind.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/_graph_pickler.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/bias.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fully_shard.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/scribe.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_tp_conv.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_template_kernel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/common_optimizers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_ordered_set.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/jagged_lowerings.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/sac_estimator.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_exporter_legacy.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_tensors.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/sym_node.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/aoti_call_delegate.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/create_parameter_op.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/printers.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/iter.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/quantizer/xpu_inductor_quantizer.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cpu_vec_isa.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_cpu.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/compile_time_profiler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/map.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/nnpack/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_export/serde/dynamic_shapes.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/operator.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_visualize_sharding.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/bias.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/ATen/cpu/vec/sve", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/bias.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/while_loop.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/ac_logging_utils.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_fx_passes.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fully_shard.py", "/usr/lib64/python3.11/site-packages/torch/distributions/__pycache__/inverse_gamma.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__pycache__/fully_shard.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/quantization/_quantized_conversions.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/coordinate_descent_tuner.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/flex_attention.py", "/usr/lib64/python3.11/site-packages/torch/fx/passes/utils/matcher_with_name_node_map_utils.py", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/simd.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/module_tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comms.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_lazy_graph_module.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/lazy.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/map.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_flex_attention_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_redistribute.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_break_hints.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/efficient_conv_bn_eval.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/fx.py", "/usr/lib64/python3.11/site-packages/torch/quantization/__pycache__/_quantized_conversions.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/_MixedMMH100.py", "/usr/lib64/python3.11/site-packages/torch/_library/fake_class_registry.py", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/model_attr_mutation.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MixedMMH100.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/xpu", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_cpu.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_pointwise_ops.py", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/config.py", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_size_docs.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_fx_passes.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compile_fx_subproc.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/builtins.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_size_docs.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_IR.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_autocast_with_hop_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/dispatch_and_compile_graph.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_18.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/_lazy_import.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/device_interface.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/tools.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/ops_handler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/triton_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_3.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/addmm_pattern.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/remove_runtime_assertions.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/replace_set_grad_with_hop_pass.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_import_utils.py", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/autograd.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_benchmark_request.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_9.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/extern_node_serializer.py", "/usr/lib64/python3.11/site-packages/torch/utils/_thunk.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_isolated.py", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/stable", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_math_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/rendezvous/__pycache__/_etcd_stub.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/torchbind_impls.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/test/c10_string_util_test", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_appending_byte_serializer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/dedupe_symint_uses.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/functools.py", "/usr/lib64/python3.11/site-packages/torch/backends/kleidiai/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/triton_kernel_wrap.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/gemm_template.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/funcname_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/device_mesh.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/share/cmake/Caffe2/public/xpu.cmake", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/infer_schema.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_func_map.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_lazy_graph_module.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_template.py", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/functional_tensor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_functools.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/experimental/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/streams.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/microbatch.py", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/non_strict_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_tp_transform.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/mha", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/core.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_param.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_capture_strategies.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/code_context.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_collective_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/autograd.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_torch/c", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/compile_tasks.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/logger.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/scan.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_region_tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/_torchlib_registry.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_op_schema.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_collectives.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_config_module.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight", "/usr/lib64/python3.11/site-packages/torch/_inductor/freezing_utils.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/flat_apply.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_conv_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/dedupe_symint_uses.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/optim/__pycache__/_deprecation_warning.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/converter.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/itertools.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_errors.py", "/usr/lib64/python3.11/site-packages/torch/backends/nnpack", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_streambase.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_affine_quantization.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/callback.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/two_tensor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/input_output_analysis.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/block_analysis.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/pt2_archive_constants.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/mps.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cudagraph_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_cpp_scheduling.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/passes/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_11.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/kleidiai/__init__.py", "/usr/lib64/python3.11/site-packages/torch/compiler/config.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_reporting.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_2.py", "/usr/lib64/python3.11/site-packages/torchgen/__pycache__/gen_schema_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/c10/xpu", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_common.py", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_checkpointable.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/microbatch.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/triton_heuristics.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/autotune_cache.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/_attention.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_backward.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/autoheuristic.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/rocm_template_buffer.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/micro_pipeline_tp.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/_unflatten.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_capture_strategies.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/executorch_call_delegate.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/flat_apply.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_9.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/dispatch_and_compile_graph.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/aoti_call_delegate.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/associative_scan.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_checkpointer.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/replace_autocast_with_hop_pass.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/flex_decoding.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/mtia/__init__.py", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/random.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/output_code.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_flex_attention_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/fake_impls.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/halide_helpers.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/micro_pipeline_tp.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cuda_cpp_scheduling.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/common_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpu_device_op_overrides.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/nnpack/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/streams.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/logging_handlers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/placement_types.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/printers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/numeric_utils.py", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/numbers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__init__.py", "/usr/lib64/python3.11/site-packages/torch/compiler/__pycache__/_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/dynamic_shapes.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/create_parameter_op.py", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/graph_transform_observer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/gds.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MMRankingA100.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/port_metadata_pass.py", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_backward_state.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MixedMMA100.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/device_mesh.py", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_graph_pickler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_decomp.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MixedMMA100.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_kernel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_grouped_gemm_template.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_sharding_prop.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/profiler/standalone", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_utils.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_numeric_debugger.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/_trace.py", "/usr/lib64/python3.11/site-packages/torch/xpu/_gpu_trace.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_quantized_ops_with_standard_ops_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/_gpu_trace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_comm_mode.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_filelock.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_utils.py", "/usr/lib64/python3.11/site-packages/torch/mtia", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_IR.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributions/inverse_gamma.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_flags.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/memory_planning.py", "/usr/lib64/python3.11/site-packages/torch/utils/_cpp_embed_headers.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_import_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_analysis.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/decomp_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/knapsack.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_conv_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_backward.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_safeguard.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__init__.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_thunk.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/cpu_vec_isa.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_version.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda_combined_scheduling.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/printers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/traced_function_transforms.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cpp_builder.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/triton_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_cpu_array_ref.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/tunable.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/cpp_wrapper", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_with_hop_pass_util.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/amp/__pycache__/grad_scaler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/common_optimizers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cuda_combined_scheduling.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/_fake_tensor_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/choices.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_bundler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/dispatch_and_compile_graph.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/collect_metadata_analysis.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__pycache__/gemm_operation_extensions.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/knapsack_evaluator.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/fuzzer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_matrix_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/functional_tensor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/choices.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_4.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_kernel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/sac_estimator.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/sdpa.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/__pycache__/decomposition_skip.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_extension.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_dynamic_shapes.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/auto_functionalize.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_dtensor_spec.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/sac_ilp.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/knapsack.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compile_fx_subproc.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_constant_symnode.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/dedupe_symint_uses.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_param.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/subproc_pool.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_gpu.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/flex_attention.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/remote_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/hop.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_env.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/triton.py", "/usr/lib64/python3.11/site-packages/torch/backends/kleidiai/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/knapsack_evaluator.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/cache_size.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/sys.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/aoti_hipify_utils.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/export_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_symmetric_memory/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/run_const_graph.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/_torchlib_registry.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_einsum_strategy.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_10.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_constant_symnode.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/agent/server/__pycache__/health_check_server.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/cuda/cutlass_utils.cuh", "/usr/lib64/python3.11/site-packages/torch/accelerator", "/usr/lib64/python3.11/site-packages/torch/backends/cusparselt", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/schedules.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_common_rules.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/FakeProcessGroup.hpp", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/flex_decoding.py", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_dynamism.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_analysis.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_7.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_common_rules.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/GroupRegistry.hpp", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/autoheuristic_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compiler_bisector.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/subgraph_lowering.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/_trace_wrapped_higher_order_op.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/_comm_mode.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/fsdp2_mem_tracker.py", "/usr/lib64/python3.11/site-packages/torch/accelerator/_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_symmetric_memory/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_19.py", "/usr/lib64/python3.11/site-packages/torch/utils/_filelock.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mkldnn_lowerings.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_15.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/dynamic_shapes.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/constant_folding.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/flex_decoding.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comm_analysis.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/__pycache__/loss.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/gds.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/amp/grad_scaler.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/ops_handler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/torchbind.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__pycache__", "/usr/lib64/python3.11/site-packages/torch/backends/cusparselt/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__init__.py", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_streambase.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/accelerator/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/device_mesh.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_cpp_scheduling.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/intra_node_comm.hpp", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/_MixedMMA100.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/memory.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cpu_vec_isa.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/model_attr_mutation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__pycache__/fallback_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__pycache__/device_op_overrides.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/autotune_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_gpu.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/mem_tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/iter.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/simple_registry.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_remove_effect_tokens_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/debug_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_async_thread_executor.py", "/usr/lib64/python3.11/site-packages/torch/fx/passes/runtime_assert.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/autograd_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/accelerator/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_tensor_ops.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_gemm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/device_interface.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/symbol.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/jagged_lowerings.py", "/usr/lib64/python3.11/site-packages/torch/distributed/optim/_deprecation_warning.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/debug_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/symbolic_opset20.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/staging.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_micro_gemm.py", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_wrapper_cpu_array_ref.py", "/usr/lib64/python3.11/site-packages/torch/include/c10/xpu/impl", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_backport_slots.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_view_ops.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_package", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_executor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/_backward.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/subproc_pool.py", "/usr/lib64/python3.11/site-packages/torch/quantization/__pycache__/_quantized_conversions.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/hip", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpu_device_op_overrides.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/simple_registry.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_4.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_redistribute.py", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_thread_safe_fork.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/ddp_fusion.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/autograd_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_building.py", "/usr/lib64/python3.11/site-packages/torch/testing/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/associative_scan.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_collective_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_state.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/debug_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/mps.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/_tensor_typing.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/_structures.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/scan.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/async_compile.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_schemas.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_8.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/compiler/__pycache__/_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/effects.py", "/usr/lib64/python3.11/site-packages/torch/utils/module_tracker.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/opinfo/definitions/__pycache__/nested.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/_tensorify_python_scalars.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comm_analysis.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_shards_wrapper.py", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/singleton_int.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/create_parameter_op.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__pycache__/cli_function_profiler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/exported_program.py", "/usr/lib64/python3.11/site-packages/torch/backends/cusparselt/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/sparse/__pycache__/_semi_structured_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/custom_tensor.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/device_mesh.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_einsum_strategy.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/placement_types.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/block_analysis.py", "/usr/lib64/python3.11/site-packages/torch/fx/passes/graph_transform_observer.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/sdpa.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_storage_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/memory_planning.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/build_package.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/_tensor_typing.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_wrapper_gpu.py", "/usr/lib64/python3.11/site-packages/torch/_thread_safe_fork.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/staging.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_cpp_scheduling.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/export_schema.thrift", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/state_dict.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/graph_region_tracker.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_ir_passes.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/package.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cpp_embed_headers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/halide.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/utils.py", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/user_input_mutation.py", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/union.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/sym_node.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_8.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/fake_config_module3.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_random.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_thread_executor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/_func_map.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/schemas.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/custom_ops.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cxx_pytree.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/__pycache__/scribe.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/static_module.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/itertools.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_draft_export.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/numbers.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_swap.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_constants.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/_remove_auto_functionalized_pass.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/base_hop.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cpp_embed_headers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/subprocess_handler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/device_op_overrides.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/ddp_fusion.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/quantizer/__pycache__/xpu_inductor_quantizer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/_utils.py", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/unsupported_operator.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_thunk.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_dispatching.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/custom_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/common_mkldnn.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_typing_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/auto_functionalize.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_quantized_ops_with_standard_ops_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/packaged/autograd/templates/ViewFuncs.cpp", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_core.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/schemas.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/opinfo/definitions/nested.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/kleidiai", "/usr/lib64/python3.11/site-packages/torch/include/ATen/xpu/detail", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_compat.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/builtins.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/triton_kernel_wrap.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/quantizer/__pycache__/xpu_inductor_quantizer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_C/_instruction_counter.pyi", "/usr/lib64/python3.11/site-packages/torch/nested/_internal", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_numeric_debugger.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/deterministic.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/fake_impl.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_1.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fuzzer.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/sac_estimator.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/input_output_analysis.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_registration.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_6.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/_structures.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_state_dict_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/traced_function_transforms.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_heuristics.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MMRankingH100.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/fully_shard.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/pytree.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/symbolic_opset19.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_capture_strategies.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/compile_command.py", "/usr/lib64/python3.11/site-packages/torch/jit/_script.pyi", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/_torchlib_registry.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/nnpack/__pycache__", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/_register_sharding.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/compile_command.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_api.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_api.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_shards_wrapper.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/functional_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/duplicate_dq_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/ck_universal_gemm_template.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/script_object.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/memory.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_verification.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/optional_input.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_unlift.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/stateful.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_12.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/os.py", "/usr/lib64/python3.11/site-packages/torch/test/c10_NetworkFlow_test", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_attention.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/_tree_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/format_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/constant_folding.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_storage_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/loss.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_tensor_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/reinplace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/mha/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_init.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_7.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/subclasses.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/torch_function.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/build_package.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/pgo.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_heuristics.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/knapsack_evaluator.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/rocm_template.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/runtime_estimator.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/fallback_ops.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_init.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/unsupported_operator.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cutlass_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_config.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/utils/__pycache__/matcher_with_name_node_map_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_param.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/subclass_parametrization.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/fake_collectives.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/runtime_estimator.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/funcname_cache.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_gemm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/_config.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mkldnn_lowerings.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/_gpu_trace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/knapsack.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/strict_mode.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/aoti_schema.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/torch_function.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package", "/usr/lib64/python3.11/site-packages/torch/utils/_cxx_pytree.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/ops.py", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/cli_function_profiler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_registration.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/_utils.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/mkldnn", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/dynamo_test_failures.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cpp_builder.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/map.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/reinplace.py", "/usr/lib64/python3.11/site-packages/torch/_library/autograd.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comm_lowering.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/mha/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/duplicate_dq_pass.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/two_tensor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_unflatten.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_filelock.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/cache_size.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/test/c10_cow_test", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/functional_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/gemm_operation_extensions.py", "/usr/lib64/python3.11/site-packages/torch/include/kineto", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/autoheuristic.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/nested_int.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/infer_schema.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_ir_passes.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_typing_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/tunable.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/gemm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/deterministic.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_onnx_program.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_ir_passes.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/stage.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_version.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/utils.py", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/symbolic_opset20.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/packaged/autograd/__pycache__/gen_view_funcs.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/memory_planning.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/subclasses.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/triton_bundler.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/flat_apply.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/_node_metadata_hook.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_view_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_random_ops.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_7.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_import_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/test/c10_generic_math_test", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/_MMRankingH100.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/dtype_propagation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/sparse/__pycache__/_triton_ops_meta.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__init__.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/mkldnn/xpu", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_template_buffer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/sac_ilp.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_trace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/_exporter_legacy.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/fake_config_module.py", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/memory.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/mm_pattern.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/custom_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__pycache__/fully_shard.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_universal_gemm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/mock_cache.py", "/usr/lib64/python3.11/site-packages/torch/utils/_config_module.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/aoti_eager.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_random_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_bmm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_19.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_tp_conv.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/runtime_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_dispatch.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/comm_analysis.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/package.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/share/cmake/Caffe2/FindCUDSS.cmake", "/usr/lib64/python3.11/site-packages/torch/_inductor/script.ld", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_conv_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/dynamic_shapes.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/efficient_conv_bn_eval.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/torch_function.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/non_strict_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/cudagraph_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/runtime_assert.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__init__.py", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/fake_class_registry.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/recording.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_helpers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/control_plane.py", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__pycache__/config.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_dedup_save_plans.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/foreach_map.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_16.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/b2b_gemm.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/_utils.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/base_hop.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_embedding_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/static_module.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/logger.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/constant_folding.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/subclass_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/pgo.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module2.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm", "/usr/lib64/python3.11/site-packages/torch/test/c10_lazy_test", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/extern_node_serializer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_storage_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/rocm_cpp_scheduling.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/memory.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_18.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_register_sharding.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/mkldnn/xpu/detail", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_errors.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/tensor_version_op.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/_debug.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_deduplication.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/placement_types.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/executorch_call_delegate.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/common_state_dict.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/unflatten.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/decomp_utils.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_autocast_with_hop_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_extension.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_6.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mkldnn_ir.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_1.py", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/schema_check.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_exposed_in.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/test/c10_ArrayRef_test", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/_tensorify_python_scalars.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/experimental", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_pointwise_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/lazy.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_get_clean_triton.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/analyze_preserves_zero_mask.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/bmm_pattern.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_func_map.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_serialization.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_13.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/NanCheck.hpp", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/hints_wrap.py", "/usr/lib64/python3.11/site-packages/torch/xpu/memory.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/loader.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/watchdog.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_fx_passes.py", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/symbol.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/hop_db.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/repro/__pycache__/aoti.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_verification.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/__pycache__/common_state_dict.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/custom_obj.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__init__.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_testing.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/__pycache__/structured.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/accelerator/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/common_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/_trace_wrapped_higher_order_op.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_fx_subproc.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/ops_handler.py", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__init__.py", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_dynamism.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/subgraph_lowering.py", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/memory.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/dtype_propagation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_unflatten.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/profiler/python", "/usr/lib64/python3.11/site-packages/torch/utils/_backport_slots.py", "/usr/lib64/python3.11/site-packages/torch/utils/serialization", "/usr/lib64/python3.11/site-packages/torch/_inductor/mkldnn_ir.py", "/usr/lib64/python3.11/site-packages/torch/_library/custom_ops.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/os.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_11.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/metrics_context.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/rocm_benchmark_request.py", "/usr/lib64/python3.11/site-packages/torch/export/passes/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_process_executor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/fx.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cpu/amp/__pycache__/grad_scaler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_redistribute.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_dedup_save_plans.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_PadMMA100.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_checkpointable.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_op_coverage.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module2.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/ilp_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/graph_info_provider.py", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_flags.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/cpp_builder.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/remote_cache.py", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/fake_impl.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/invoke_subgraph.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_dynamic_shapes.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/multi_kernel.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_isolated.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/freezing_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/mm_scaled.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_14.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/_invoke_quant.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/dynamo_test_failures.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_config.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/__pycache__/gen_aoti_c_shim.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MMRankingH100.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/halide.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/scan.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/mps_device_op_overrides.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/mm_scaled.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/input_output_analysis.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_onnx_program.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/compile_tasks.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_common.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/version.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_state.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_tp_transform.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/__pycache__/structured.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/halide.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_trace.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/b2b_gemm.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/mtia/_utils.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_dispatching.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/repro/__pycache__/aoti.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/opinfo/definitions/__pycache__/nested.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_PadMMA100.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_dispatch.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/_fake_tensor_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/__pycache__/_flat_param.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/ac_logging_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_compat.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/nested_tensor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/common_mkldnn.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/symbolic_opset20.py", "/usr/lib64/python3.11/site-packages/torch/export/passes", "/usr/lib64/python3.11/site-packages/torch/_strobelight/cli_function_profiler.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/remote_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_embedding_ops.py", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/Functional.hpp", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/loader.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_environment.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/comms.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_symmetric_memory/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/funcname_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/converter.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_benchmark_request.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/test/cpu_allocator_test", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/staging.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/misc_patterns.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/_visualize_sharding.py", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/_dynamism.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/mem_tracker.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/schedules.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/learnedheuristic_interface.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/mm_pattern.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_param_group.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_remove_auto_functionalized_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/comms.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__init__.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_lazy_import.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_safeguard.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_isolated.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cuda_env.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_micro_gemm.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_fx_ext.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/nested_int.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/pgo.py", "/usr/lib64/python3.11/site-packages/torch/optim/__pycache__/_adafactor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/__pycache__/device_op_overrides.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/aoti_runtime", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_process_executor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/cache_dir_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__pycache__", "/usr/lib64/python3.11/site-packages/torch/export/custom_obj.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/output_code.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/pytree.py", "/usr/lib64/python3.11/site-packages/torch/export/_swap.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/core.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/replace_set_grad_with_hop_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/hints.py", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/_IR.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/custom_tensor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_strobelight", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/unflatten.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/graph_info_provider.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/nested_tensor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_decomp.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/misc_patterns.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/xpu", "/usr/lib64/python3.11/site-packages/torch/compiler/_cache.py", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_state_dict_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/lift_constants_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_compat.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/fake_class_registry.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/mm_scaled.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_matrix_ops.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/script_object.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/common_optimizers.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/custom_graph_pass.py", "/usr/lib64/python3.11/site-packages/torch/utils/_exposed_in.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/sys.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/compile_command.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/__pycache__/gen_aoti_c_shim.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/benchmarking.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/optional_input.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/subclass_parametrization.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_grouped_gemm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/sparse/_triton_ops_meta.py", "/usr/lib64/python3.11/site-packages/torch/test/c10_error_test", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/triton.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/common_mkldnn.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_api.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/async_compile.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/dtype_propagation.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/lift_constants_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/cpp_wrapper/device_internal", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_common_rules.py", "/usr/lib64/python3.11/site-packages/torch/distributed/optim/__pycache__/_deprecation_warning.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__pycache__/_paged_attention.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_dispatching.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_3.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/format_utils.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/trace_rules.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/port_metadata_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_checkpointer.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_5.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/unflatten.py", "/usr/lib64/python3.11/site-packages/torch/testing/_utils.py", "/usr/lib64/python3.11/site-packages/torch/_vendor/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_debug.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_experimental_ops.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/custom_graph_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/hop_db.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/exported_program.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/runtime_assert.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MMRankingA100.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_8.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/user_input_mutation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_environment.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/fake_impl.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_10.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/subclass_utils.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/fake_config_module2.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/nested_int.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cuda_kernel.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/ddp_fusion.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/autotune_cache.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/serialization/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/comm_lowering.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_view_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_runtime", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/ck_template.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/agent/server/__pycache__/health_check_server.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_sharding_prop.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mock_cache.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/lift_constants_pass.py", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/schema_check.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/jit_compile_runtime_wrappers.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/stateful.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_ordered_set.py", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/memory.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/insert_custom_op_guards.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/simd.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/symbol.py", "/usr/lib64/python3.11/site-packages/torch/export/experimental/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_15.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/ilp_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_19.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/infer_schema.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/gemm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/watchdog.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/triton.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/_paged_attention.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/choices.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/mps_device_op_overrides.py", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/compile_time_profiler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/__pycache__/singleton_int.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/hints_wrap.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/torchbind.py", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/_backward_state.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/sys.py", "/usr/lib64/python3.11/site-packages/torch/export/experimental/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/mha/__init__.py", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__pycache__", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_config_module.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/symbolic_opset19.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/autoheuristic_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_exposed_in.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/compiler/__pycache__/config.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/mod_tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/lazy.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/subclass_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/flex_attention.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/experimental/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_dynamo/graph_break_hints.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/addmm_pattern.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_9.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/functional_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_grouped_gemm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_compat.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/simd_kernel_features.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_matrix_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/user_input_mutation.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/compile_tasks.py", "/usr/lib64/python3.11/site-packages/torch/backends/kleidiai", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/aoti_hipify_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/_op_coverage.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_random.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/test_case.py", "/usr/lib64/python3.11/site-packages/torch/backends/cusparselt/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/fsdp2_mem_tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/invoke_subgraph.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/module_tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/device_op_overrides.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/subclasses.py", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/coordinate_descent_tuner.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/cache_dir_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__", "/usr/lib64/python3.11/site-packages/torch/__pycache__/_thread_safe_fork.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/tensor_version_op.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/learnedheuristic_interface.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_building.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/fake_impls.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_4.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/sac_ilp.py", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/export_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/triton_combo_kernel.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/ck_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/runtime_wrappers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/_backward_state.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_draft_export.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/decomposition_skip.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_env.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/__pycache__/iter.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/learned_heuristic_controller.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/xpu/device_op_overrides.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cutlass_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributions/__pycache__/inverse_gamma.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/while_loop.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_experimental_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/device_op_overrides.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/tensor_version_op.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/_adafactor.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/runtime_estimator.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/logger.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cuda_template.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/logging_handlers.py", "/usr/lib64/python3.11/site-packages/torch/export/experimental/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/jit_compile_runtime_wrappers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/aoti_schema.py", "/usr/lib64/python3.11/site-packages/torch/export/_draft_export.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_hf_storage.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_17.py", "/usr/lib64/python3.11/site-packages/torch/_subclasses/functional_tensor.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops", "/usr/lib64/python3.11/site-packages/torch/_library/simple_registry.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/base_hop.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/schedules.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_appending_byte_serializer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cpu/amp/grad_scaler.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/logging_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/_serialization.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_streambase.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_region_tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_hf_storage.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/state_dict.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/callback.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/sparse/__pycache__/_triton_ops_meta.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/constant_folding.py", "/usr/lib64/python3.11/site-packages/torch/export/graph_signature.py", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/FlightRecorder.hpp", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_include", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_api.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_13.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/metrics_context.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/accelerator/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/device_interface.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/triton_bundler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/benchmarking.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/custom_graph_pass.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_onnx_program.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_collective_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/rendezvous/_etcd_stub.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/insert_custom_op_guards.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/itertools.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/loop_body.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/_remove_effect_tokens_pass.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/fx.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_visualize_sharding.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/aoti_eager.py", "/usr/lib64/python3.11/site-packages/torch/_export/serde/union.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/fake_collectives.py", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_cxx_pytree.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_async_executor.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/async_compile.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/output_code.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_compat.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/decompose_mem_bound_mm.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/triton_helpers.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/native/nested", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_split_scan.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/aoti_hipify_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/multi_kernel.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_symmetric_memory/__pycache__", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/profiler/unwind", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compile_fx_ext.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/kleidiai/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_unlift.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/associative_scan.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_core.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/analyze_preserves_zero_mask.py", "/usr/lib64/python3.11/site-packages/torch/_library/utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_12.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__", "/usr/lib64/python3.11/site-packages/torch/utils/_typing_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_comm_mode.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/distributed.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/flex_attention.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/mm_pattern.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/operator.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/core.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp/__pycache__", "/usr/lib64/python3.11/site-packages/torch/cuda/gds.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/handlers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/__pycache__/_flat_param.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/learnedheuristic_interface.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/_constant_symnode.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/block_analysis.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_collectives.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/timer/debug_info_logging.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_cpp_scheduling.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_10.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_constants.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/numeric_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_symmetric_memory", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpu_device_op_overrides.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_combo_kernel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/pt2_archive_constants.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/misc_patterns.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/hints.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/rocm_kernel.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/kernel/__pycache__/flex_attention.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/replace_with_hop_pass_util.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_dtensor_spec.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/strict_mode.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/b2b_gemm.py", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/optional_input.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_micro_gemm.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/auto_functionalize.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/insert_custom_op_guards.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/executorch_call_delegate.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/os.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_reporting.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_backport_slots.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/cli_function_profiler.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_conv_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/__pycache__/cuda_kernel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/triton_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/optim/__pycache__/_adafactor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/model_attr_mutation.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_experimental_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/mod_tracker.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/numeric_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/constant_folding.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/addmm_pattern.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_dtensor_spec.py", "/usr/lib64/python3.11/site-packages/torch/_vendor/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/triton_split_scan.py", "/usr/lib64/python3.11/site-packages/torch/fx/passes/__pycache__/graph_transform_observer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/debug/__pycache__/_op_coverage.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_functools.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_bmm_template.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/cache_size.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/run_const_graph.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/triton_split_scan.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/decompose_mem_bound_mm.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/memory.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/callback.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_registration.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/dynamic_shapes.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/coordinate_descent_tuner.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_remove_auto_functionalized_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_size_docs.py", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_template_kernel.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_random.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/graph_break_hints.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torchgen/__pycache__/gen_schema_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/ops/__pycache__/hop.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/_invoke_quant.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_triton.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__/_register_sharding.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_remove_effect_tokens_pass.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/mkldnn_lowerings.py", "/usr/lib64/python3.11/site-packages/torch/accelerator/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/build_package.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/logging_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/tools.py", "/usr/lib64/python3.11/site-packages/torch/onnx/__pycache__/_flags.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/_tp_transform.py", "/usr/lib64/python3.11/site-packages/torch/export/passes/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/distributed.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/subgraph_lowering.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_gemm_template.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compile_fx_ext.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_C/_cusparselt.pyi", "/usr/lib64/python3.11/site-packages/torch/sparse/__pycache__/_semi_structured_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/flex_attention.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/cudagraph_utils.py", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/device_mesh.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/union.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/_MixedMMH100.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/__pycache__/_get_clean_triton.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_collectives.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__pycache__", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/hop_db.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/compiler_bisector.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/code_context.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_18.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/analyze_preserves_zero_mask.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/SymmetricMemory.hpp", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/simd.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/_affine_quantization.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/foreach_map.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_sympy/singleton_int.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/sdpa.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/static_module.py", "/usr/lib64/python3.11/site-packages/torch/utils/_get_clean_triton.py", "/usr/lib64/python3.11/site-packages/torch/_vendor/packaging/__pycache__/version.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/_debug.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_flex_attention_template.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compiler_bisector.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/effects.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/while_loop.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_math_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/learned_heuristic_controller.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/experimental/__pycache__", "/usr/lib64/python3.11/site-packages/torch/share/cmake/Caffe2/FindSYCLToolkit.cmake", "/usr/lib64/python3.11/site-packages/torch/_dynamo/metrics_context.py", "/usr/lib64/python3.11/site-packages/torch/_library/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/_invoke_quant.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/__pycache__/_gpu_trace.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/variables/sdpa.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_17.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/compiler/__pycache__/config.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/sdpa.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_dedup_save_plans.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/logging_handlers.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_14.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/passes/__pycache__/_node_metadata_hook.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_3.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/aoti_runtime/interface.cpp", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_random_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/parallel/__pycache__/loss.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/__pycache__/_math_ops.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_2.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/microbatch.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/backends/mha/__pycache__", "/usr/lib64/python3.11/site-packages/torch/utils/_functools.py", "/usr/lib64/python3.11/site-packages/torch/_C/_export.pyi", "/usr/lib64/python3.11/site-packages/torch/export/_safeguard.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_wrapper_cpu_array_ref.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/packaged/autograd/__pycache__/gen_view_funcs.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/inductor/aoti_torch/generated", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/multiprocessing/subprocess_handler/__pycache__/subprocess_handler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/RankLocal.hpp", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/traced_function_transforms.py", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/exported_program.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/sym_node.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/_numeric_debugger.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_13.py", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/loader.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/export_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_op_schema.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/mem_tracker.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__pycache__/gemm_operation_extensions.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/dynamo_test_failures.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/_sfdp_pattern_5.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/custom_tensor.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/recording.py", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fully_shard.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_12.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/db/examples/__pycache__/unsupported_operator.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/__pycache__/_lazy_import.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/schema_check.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/halide_helpers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/custom_ops.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_checkpointer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/dynamic_shapes.py", "/usr/lib64/python3.11/site-packages/torchgen/gen_aoti_c_shim.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/polyfills/__pycache__/operator.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_decomp.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/watchdog.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/multi_kernel.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/efficient_conv_bn_eval.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/__pycache__/_shards_wrapper.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/distributed/__pycache__/common_state_dict.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/cuda/_gpu_trace.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/loop_body.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_tp_conv.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/ac_logging_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/mkldnn_ir.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/runtime_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/micro_pipeline_tp.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/fx/experimental/__pycache__/recording.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/__pycache__/pt2_archive_constants.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/test_case.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_hf_storage.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/simd_kernel_features.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/_async_thread_executor.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/package/package.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_state_dict_utils.py", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_strobelight/compile_time_profiler.py", "/usr/lib64/python3.11/site-packages/torch/nested/_internal/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_testing.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_schemas.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/cache_dir_utils.py", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/fake_config_module.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/two_tensor.py", "/usr/lib64/python3.11/site-packages/torch/_dynamo/__pycache__/_trace_wrapped_higher_order_op.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/flex_attention.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/stage.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_testing.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/__pycache__/learned_heuristic_controller.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/__pycache__/format_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/utils/_strobelight/__pycache__/cli_function_profiler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/mps_device_op_overrides.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_param_group.py", "/usr/lib64/python3.11/site-packages/torch/fx/_lazy_graph_module.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/common_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_tree_utils.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/__main__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_functorch/_activation_checkpointing/__pycache__/graph_info_provider.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/autoheuristic.py", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/__pycache__/decompose_mem_bound_mm.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/mtia/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_async_process_executor.py", "/usr/lib64/python3.11/site-packages/torch/_functorch/_aot_autograd/__pycache__/collect_metadata_analysis.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_template_buffer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_export/__pycache__/non_strict_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_constants.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/_swap.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/__pycache__/device_mesh.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/_unlift.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/compile_worker/__pycache__/subproc_pool.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/triton_compat.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/extern_node_serializer.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/fake_collectives.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/__pycache__/triton_helpers.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/pipelining/__pycache__/__init__.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/_torchlib/_tensor_typing.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_analysis.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/streams.py", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/agent/server/health_check_server.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/foreach_map.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/fx/__pycache__/decomposition_skip.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/effects.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/elastic/timer/__pycache__/debug_info_logging.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/cpu/amp/__pycache__/grad_scaler.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/_fsdp_api.py", "/usr/lib64/python3.11/site-packages/torch/sparse/_semi_structured_ops.py", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_higher_order_ops/__pycache__/hints_wrap.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__pycache__/_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/aoti/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/nn/attention/__pycache__/flex_attention.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/__pycache__/rocm_template.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/include/torch/csrc/distributed/c10d/CUDASymmetricMemory.hpp", "/usr/lib64/python3.11/site-packages/torch/ao/quantization/pt2e/__pycache__/_affine_quantization.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/onnx/_internal/exporter/__pycache__/_dynamic_shapes.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/export/__pycache__/custom_obj.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/rocm/ck_conv_template.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cpp_wrapper_cpu.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_1.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_logging/__pycache__/scribe.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/__init__.py", "/usr/lib64/python3.11/site-packages/torch/distributed/tensor/_ops/_einsum_strategy.py", "/usr/lib64/python3.11/site-packages/torch/distributed/checkpoint/_version.py", "/usr/lib64/python3.11/site-packages/torch/_strobelight/__pycache__/cli_function_profiler.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/testing/_internal/__pycache__/torchbind_impls.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/__init__.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/runtime/benchmarking.py", "/usr/lib64/python3.11/site-packages/torch/_export/passes/remove_runtime_assertions.py", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/fake_impls.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/xpu/random.py", "/usr/lib64/python3.11/site-packages/torch/_export/serde/__pycache__/aoti_schema.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/distributed/_tools/__pycache__/fsdp2_mem_tracker.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/jagged_lowerings.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/__pycache__/cpp_bmm_template.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_subclasses/__pycache__/_fake_tensor_utils.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torchgen/gen_schema_utils.py", "/usr/lib64/python3.11/site-packages/torch/_inductor/fx_passes/serialized_patterns/__pycache__/_sfdp_pattern_15.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/autoheuristic/artifacts/_PadMMA100.py", "/usr/lib64/python3.11/site-packages/torch/distributed/_composable/fsdp", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_api.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/test/c10_Scalar_test", "/usr/lib64/python3.11/site-packages/torch/include/c10/metal", "/usr/lib64/python3.11/site-packages/torch/distributed/fsdp/_fully_shard/__pycache__/_fsdp_common.cpython-311.opt-1.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/codegen/cuda/cutlass_lib_extensions/__pycache__/__init__.cpython-311.pyc", "/usr/lib64/python3.11/site-packages/torch/_inductor/loop_body.py", "/usr/lib64/python3.11/site-packages/torch/include/ATen/cpu/vec/vec256/zarch", "/usr/lib64/python3.11/site-packages/torch/_inductor/__pycache__/test_case.cpython-311.pyc"]}, "rpm abi": {"diff": {"old": ["libjitbackend_test.so", "libbackend_with_compiler.so", "libc10.so", "libtorch_python.so", "libtorch_cpu.so", "libtorchbind_test.so", "_C.cpython-311-aarch64-linux-gnu.so"], "new": ["libjitbackend_test.so", "libbackend_with_compiler.so", "libc10.so", "libtorch_python.so", "libtorch_cpu.so", "libtorchbind_test.so", "_C.cpython-311-aarch64-linux-gnu.so"]}}, "rpm header": {"diff": {"old": ["_linalg_det_native.h", "_has_same_storage_numel_native.h", "erfc.h", "_sparse_mm_reduce_impl.h", "zero.h", "isposinf_ops.h", "_test_ambiguous_defaults_ops.h", "_sparse_log_softmax_ops.h", "pybind.h", "KernelFunction.h", "conj_physical_ops.h", "_scaled_dot_product_efficient_attention_backward.h", "renorm_meta.h", "roll_native.h", "take.h", "CUDAFunctions.h", "gelu_meta.h", "_convert_indices_from_csr_to_coo_ops.h", "vec512_int.h", "thnn_conv2d.h", "linalg_inv_ex_meta.h", "min.h", "log_normal_compositeexplicitautograd_dispatch.h", "_native_multi_head_attention_native.h", "_pdist_backward.h", "_copy_from_ops.h", "_foreach_erfc.h", "mean_compositeexplicitautograd_dispatch.h", "miopen_convolution_relu.h", "smm_native.h", "dsplit_ops.h", "linalg_lstsq_cpu_dispatch.h", "_nested_tensor_from_mask_left_aligned_ops.h", "binary_cross_entropy_backward.h", "_to_sparse_csr_cpu_dispatch.h", "_unsafe_index_put_ops.h", "_copy_from_native.h", "special_bessel_j1_meta.h", "unique_dim_consecutive_native.h", "minimum_native.h", "zeros_like_ops.h", "convolution_ops.h", "le.h", "cudnn_convolution_transpose_native.h", "object.h", "fake_quantize_per_tensor_affine_ops.h", "mkldnn_linear_backward_ops.h", "_adaptive_avg_pool2d_backward_native.h", "tril.h", "linalg_matrix_power_native.h", "_copy_from_and_resize_native.h", "mvlgamma_ops.h", "vdot_native.h", "special_i0e.h", "sum_to_size.h", "fill.h", "_slow_conv2d_forward_native.h", "Activation.h", "fractional_max_pool2d_backward_meta.h", "ones_like_ops.h", "_histogramdd_bin_edges_cpu_dispatch.h", "t_copy_ops.h", "_make_dual_copy_ops.h", "_native_batch_norm_legit_cuda_dispatch.h", "col_indices_copy_native.h", "binary_cross_entropy_cpu_dispatch.h", "_to_sparse_bsr_cpu_dispatch.h", "ir_simplifier.h", "logical_not.h", "onnx.h", "to_dense_backward_compositeimplicitautograd_dispatch.h", "jit_exception.h", "_masked_softmax_cuda_dispatch.h", "graph_rewrite_helper.h", "norm_meta.h", "_neg_view_native.h", "sequential.h", "embedding_bag_native.h", "scalar_tensor_native.h", "triu_indices_cpu_dispatch.h", "cudnn_affine_grid_generator_ops.h", "sparse_bsc_tensor_native.h", "gather_backward_ops.h", "function_schema_inl.h", "triangular_solve_native.h", "cumsum_meta_dispatch.h", "ParallelFuture.h", "upsample_nearest1d_meta_dispatch.h", "vec256_double.h", "DispatchStub.h", "constant_pad_nd.h", "upsample_nearest3d_backward.h", "item.h", "gru.h", "fft_ifft2_native.h", "block_diag.h", "conv_transpose3d_native.h", "_test_autograd_multiple_dispatch_ops.h", "linalg_cholesky_ex_meta.h", "or.h", "linalg_ldl_factor.h", "special_laguerre_polynomial_l_ops.h", "igamma_meta.h", "_foreach_div.h", "special_logit.h", "MPSEvent.h", "special_shifted_chebyshev_polynomial_u.h", "InlineEvent.h", "_fused_dropout.h", "_upsample_nearest_exact3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "randint_like_ops.h", "sym_constrain_range_for_size_ops.h", "argmin_ops.h", "cudnn_convolution_native.h", "adaptive_avg_pool3d.h", "triu.h", "interned_strings.h", "t_copy.h", "fft_hfft_compositeimplicitautograd_dispatch.h", "_fused_adam.h", "reduction.h", "adaptive_max_pool2d_backward_meta.h", "_new_zeros_with_same_feature_meta.h", "graph_iterator.h", "_nested_tensor_from_mask_native.h", "quantize_per_tensor_dynamic.h", "sym_stride_ops.h", "QuantizerBase.h", "mT.h", "FunctionTraits.h", "register_ops_common_utils.h", "hamming_window_compositeexplicitautograd_dispatch.h", "python_torch_functions.h", "fliplr_ops.h", "native_channel_shuffle.h", "avg_pool3d_meta_dispatch.h", "disable_torch_function.h", "gather_native.h", "VmapGeneratedPlumbing.h", "upsample_bilinear2d_backward.h", "to.h", "pass_manager.h", "_foreach_cosh.h", "log_normal_meta_dispatch.h", "sym_storage_offset.h", "DispatchKey.h", "MT19937RNGEngine.h", "conv_tbc.h", "name_mangler.h", "vander.h", "_cudnn_rnn.h", "_sparse_mask_projection_ops.h", "upsample_nearest2d_meta_dispatch.h", "_nested_select_backward_ops.h", "_prelu_kernel.h", "python_print.h", "miopen_convolution_transpose_compositeexplicitautograd_dispatch.h", "sort_meta_dispatch.h", "geometric_ops.h", "perf-inl.h", "_cast_Float_native.h", "SizesAndStrides.h", "_reshape_from_tensor_native.h", "guard_elimination.h", "kaiser_window_ops.h", "avg_pool2d_backward_meta.h", "miopen_depthwise_convolution.h", "frac_ops.h", "variadic.h", "fft.h", "mps_convolution_transpose_backward_native.h", "topk_ops.h", "_test_check_tensor_ops.h", "_masked_scale_native.h", "_log_softmax_backward_data_meta.h", "to_sparse_csc_native.h", "special_scaled_modified_bessel_k1_meta.h", "_coalesced.h", "TensorBody.h", "isfinite_ops.h", "diag_embed_ops.h", "_unsafe_view_native.h", "_to_dense_compositeexplicitautograd_dispatch.h", "addr_native.h", "tile_ops.h", "concatenate.h", "torch_dispatch_mode.h", "rrelu_with_noise_native.h", "_dim_arange.h", "lt.h", "minimum_ops.h", "sum_to_size_native.h", "index_reduce_native.h", "softplus_native.h", "diff_ops.h", "_slow_conv2d_backward_native.h", "mkldnn_reorder_conv3d_weight_compositeexplicitautograd_dispatch.h", "random_cpu_dispatch.h", "code_template.h", "where_ops.h", "to_padded_tensor_ops.h", "Copy.h", "fft_ifftn_native.h", "SegmentReduce.h", "_histogramdd_bin_edges_native.h", "atleast_1d_native.h", "fft_ihfft.h", "std_mean_cpu_dispatch.h", "view_as_real_copy_native.h", "alpha_dropout.h", "sinc.h", "cumprod_meta_dispatch.h", "shape.h", "ger_native.h", "hardtanh_backward_native.h", "glu_native.h", "python_enum_tag.h", "replication_pad1d_backward_meta.h", "gradient_native.h", "to_sparse_csr_ops.h", "logspace.h", "concat_opt.h", "_indices_copy_native.h", "type_parser.h", "_batch_norm_impl_index_backward_native.h", "_convert_indices_from_csr_to_coo.h", "ResizeCommon.h", "example.h", "igammac_native.h", "_cast_Int_native.h", "_fft_c2c.h", "_to_sparse_bsc_native.h", "rnn_tanh.h", "log_native.h", "BinaryOps.h", "linalg_norm_ops.h", "_flash_attention_backward.h", "randn_like_compositeexplicitautograd_dispatch.h", "prod_compositeimplicitautograd_dispatch.h", "_validate_sparse_bsc_tensor_args.h", "reflection_pad1d_backward_ops.h", "_dirichlet_grad_native.h", "_linalg_check_errors_ops.h", "_values_copy_ops.h", "any_native.h", "sin_ops.h", "_upsample_nearest_exact3d_backward_native.h", "CompositeImplicitAutogradNestedTensorFunctions_inl.h", "searchsorted_cpu_dispatch.h", "object_ptr.h", "linalg_pinv_compositeexplicitautograd_dispatch.h", "log_meta.h", "sparse_coo_tensor_native.h", "is_signed_native.h", "util.h", "_foreach_log10_ops.h", "lazy_graph_executor.h", "zero_native.h", "linalg_lu_meta.h", "AdaptivePooling.h", "bitwise_right_shift_native.h", "fbgemm_linear_int8_weight.h", "pow_native.h", "unique_dim_ops.h", "_foreach_clamp_max_ops.h", "_validate_compressed_sparse_indices_native.h", "adaptive.h", "_linalg_svd_cpu_dispatch.h", "sparse_resize_and_clear_native.h", "sgn_native.h", "_functional_sym_constrain_range_for_size_compositeexplicitautograd_dispatch.h", "grid_sampler_ops.h", "is_complex_native.h", "nanquantile_ops.h", "fft_hfftn.h", "_fused_adam_ops.h", "ormqr.h", "linspace.h", "_adaptive_avg_pool2d_native.h", "dsplit.h", "sym_stride.h", "prod.h", "margin_ranking_loss.h", "unique_consecutive_ops.h", "col_indices_copy.h", "grid_sampler_3d_backward_native.h", "_masked_scale_ops.h", "TransformationHelper.h", "_histogramdd_from_bin_cts_native.h", "im2col_ops.h", "slice_compositeexplicitautograd_dispatch.h", "GridSamplerUtils.h", "rnn_relu_cell.h", "_histogramdd_from_bin_cts_compositeexplicitautograd_dispatch.h", "atan2.h", "_foreach_cosh_ops.h", "aminmax_cuda_dispatch.h", "_foreach_sinh_native.h", "cdist_ops.h", "linalg_solve_native.h", "miopen_convolution_cuda_dispatch.h", "transpose_native.h", "mkldnn_max_pool2d_ops.h", "bitwise_and_ops.h", "triangular_solve.h", "Exceptions.h", "batch_norm_backward_reduce_cuda_dispatch.h", "randint_native.h", "empty_quantized_native.h", "pad.h", "isinf.h", "to_dense_backward_native.h", "_pin_memory_ops.h", "negative_ops.h", "message.h", "nll_loss2d_backward_native.h", "base.h", "slow_conv_transpose2d_cuda_dispatch.h", "_cdist_forward.h", "sinh.h", "fft_fft2_compositeimplicitautograd_dispatch.h", "_sparse_coo_tensor_with_dims_and_tensors_ops.h", "is_same_size_native.h", "mse_loss_ops.h", "to_sparse_bsc_compositeimplicitautograd_dispatch.h", "_cslt_compress_ops.h", "_lstm_mps.h", "_sobol_engine_initialize_state_native.h", "nccl.h", "index_fill.h", "_thnn_differentiable_gru_cell_backward.h", "script_resp.h", "fliplr.h", "squeeze_copy_native.h", "python_tensor.h", "fbgemm_utils.h", "nll_loss_forward_ops.h", "sparse_csc_tensor_compositeimplicitautograd_dispatch.h", "miopen_convolution_relu_cuda_dispatch.h", "_foreach_copy_ops.h", "avg_pool3d_backward_ops.h", "_cslt_sparse_mm.h", "InlineStreamGuard.h", "integer_value_refinement.h", "hash_provider.h", "vander_ops.h", "permute_copy_ops.h", "softmax.h", "_conj_physical.h", "empty_permuted.h", "gru_cell.h", "expand_as_ops.h", "hspmm_native.h", "_nested_tensor_from_tensor_list.h", "full_compositeexplicitautograd_dispatch.h", "linalg_cross_native.h", "linear_backward_native.h", "vdot_ops.h", "CompositeImplicitAutogradFunctions_inl.h", "aminmax_ops.h", "AffineQuantizer.h", "_foreach_norm_compositeexplicitautograd_dispatch.h", "sort_compositeimplicitautograd_dispatch.h", "renorm.h", "AffineQuantizerBase.h", "nll_loss2d_forward_native.h", "adaptive_max_pool1d_ops.h", "_efficientzerotensor_native.h", "_addmm_activation_ops.h", "DLConvertor.h", "pixelshuffle.h", "cudnn_convolution_relu.h", "_mps_convolution_native.h", "make_boxed_from_unboxed_functor.h", "view_as_complex_copy_native.h", "_embedding_bag_forward_only_cuda_dispatch.h", "batch_norm_stats_ops.h", "_test_autograd_multiple_dispatch_view_copy.h", "lcm_ops.h", "fft_rfft_compositeimplicitautograd_dispatch.h", "_convert_indices_from_csr_to_coo_meta.h", "index_native.h", "_foreach_ceil.h", "split_copy_ops.h", "batch_norm_ops.h", "sym_size.h", "_sobol_engine_ff_native.h", "miopen_convolution_ops.h", "cross_compositeimplicitautograd_dispatch.h", "compiled_autograd.h", "_sparse_sum_backward.h", "_sparse_csr_tensor_unsafe_native.h", "igamma_ops.h", "queue.h", "sparse_bitset.h", "_efficient_attention_forward_ops.h", "cudnn_batch_norm_cuda_dispatch.h", "_native_batch_norm_legit_no_training_ops.h", "cudnn_batch_norm_backward_native.h", "linalg_matrix_exp_native.h", "new_empty_strided_native.h", "_foreach_lerp.h", "Layout.h", "_adaptive_avg_pool3d_backward_native.h", "linalg_cond.h", "multilabel_margin_loss_native.h", "fft_hfft2_native.h", "quantize_per_tensor_dynamic_ops.h", "hardswish_ops.h", "import_export_functions.h", "clamp_min_ops.h", "to_dense_compositeimplicitautograd_dispatch.h", "lt_ops.h", "BFloat16.h", "data_native.h", "orgqr.h", "count_nonzero_compositeexplicitautograd_dispatch.h", "linalg_eig_ops.h", "Synchronized.h", "cumsum_ops.h", "le_native.h", "round_native.h", "PythonDispatcherTLS.h", "mkldnn_rnn_layer_native.h", "binary_cross_entropy_backward_cuda_dispatch.h", "index_select_ops.h", "linalg_inv_ex_ops.h", "isinf_ops.h", "vec256_float.h", "sym_constrain_range_for_size.h", "ChannelShuffleKernel.h", "miopen_rnn_compositeexplicitautograd_dispatch.h", "quantized_max_pool1d.h", "_foreach_add_native.h", "_batch_norm_impl_index_backward_ops.h", "file_adapter.h", "reflection_pad2d_backward_native.h", "dstack_native.h", "lerp.h", "special_softmax_native.h", "linalg_ldl_factor_ex_ops.h", "corrcoef.h", "_foreach_round_ops.h", "grid_sampler_2d_backward.h", "empty_like_compositeexplicitautograd_dispatch.h", "numpy_T.h", "gradient_compositeimplicitautograd_dispatch.h", "miopen_convolution_add_relu_cuda_dispatch.h", "amin_ops.h", "_neg_view.h", "concatenate_ops.h", "special_scaled_modified_bessel_k1_ops.h", "mkldnn_max_pool3d_backward.h", "clamp_max_native.h", "CUDAPluggableAllocator.h", "instance_norm_compositeimplicitautograd_dispatch.h", "_log_softmax_backward_data.h", "fbgemm_linear_int8_weight_fp32_activation.h", "_fw_primal_ops.h", "_cudnn_init_dropout_state.h", "native_dropout_ops.h", "clamp_cuda_dispatch.h", "where.h", "reflection_pad3d.h", "_segment_reduce_backward.h", "empty_compositeimplicitautograd_dispatch.h", "lu_unpack_native.h", "from_file.h", "_amp_foreach_non_finite_check_and_unscale_native.h", "_sparse_mm_reduce_impl_backward_ops.h", "sort_ops.h", "diagonal_copy_ops.h", "pixel_unshuffle.h", "bartlett_window_native.h", "lgamma_ops.h", "special_digamma_ops.h", "gradient_ops.h", "avg_pool3d_compositeexplicitautogradnonfunctional_dispatch.h", "mean_meta.h", "stack_native.h", "sort_native.h", "sym_storage_offset_ops.h", "nll_loss_forward_meta_dispatch.h", "CPUGeneratorImpl.h", "adaptive_max_pool3d_ops.h", "Tensor.h", "scatter_reduce_ops.h", "size_ops.h", "nanmedian.h", "_reshape_alias_copy_native.h", "remove_mutation.h", "view_copy.h", "narrow_copy_ops.h", "_fused_moving_avg_obs_fq_helper_native.h", "_functional_sym_constrain_range_for_size_native.h", "_to_sparse_csc_native.h", "triu_indices_native.h", "digamma_meta.h", "iterator.h", "rnn_relu_native.h", "l1_loss_ops.h", "acosh_ops.h", "row_indices_copy.h", "backend_exception.h", "_linalg_svd_native.h", "_index_put_impl_native.h", "ComplexHelper.h", "_foreach_sin_native.h", "batch_norm_backward_elemt_native.h", "hardsigmoid.h", "FractionalMaxPooling.h", "ccol_indices_native.h", "index_copy.h", "rsub.h", "_embedding_bag_backward_native.h", "cat.h", "diagonal_backward_native.h", "DeviceType.h", "inline_loop_condition.h", "driver_api.h", "triu_indices_cuda_dispatch.h", "lift_fresh_copy.h", "rref_impl.h", "_log_softmax_backward_data_ops.h", "graph_node_list.h", "ne_native.h", "cov_native.h", "XPUHooksInterface.h", "uniform_ops.h", "TopKImpl.h", "_validate_compressed_sparse_indices_ops.h", "_pad_packed_sequence_ops.h", "TracerMode.h", "replication_pad3d.h", "_mps_convolution_compositeexplicitautograd_dispatch.h", "special_expit_ops.h", "upsample_bilinear2d_backward_native.h", "_histogramdd_from_bin_cts.h", "CUDAFunctions_inl.h", "cudnn_convolution_relu_cuda_dispatch.h", "dstack_ops.h", "cumprod_compositeimplicitautograd_dispatch.h", "conv_transpose1d.h", "special_chebyshev_polynomial_w.h", "constant_pad_nd_native.h", "upsample_bicubic2d_compositeimplicitautograd_dispatch.h", "_fake_quantize_learnable_per_tensor_affine_backward_native.h", "multilabel_margin_loss.h", "LeftRight.h", "round_ops.h", "triplet_margin_loss_native.h", "polygamma_meta.h", "max_unpool3d_ops.h", "fake_quantize_per_channel_affine_cachemask_backward.h", "polygamma_native.h", "rpc_command_base.h", "resize_as_sparse_ops.h", "data_shuttle.h", "_weight_norm_interface_backward_ops.h", "clamp_compositeexplicitautogradnonfunctional_dispatch.h", "normalization.h", "python_ir.h", "observer.h", "scaled_dot_product_attention_compositeimplicitautograd_dispatch.h", "CUDACachingAllocator.h", "_upsample_nearest_exact3d_native.h", "MPSHooks.h", "mul_ops.h", "replication_pad2d_native.h", "special_erfcx_native.h", "_linalg_det_meta.h", "is_signed.h", "upsample_bicubic2d_meta.h", "choose_qparams_optimized_native.h", "sparse_resize_and_clear.h", "is_conj_ops.h", "xlogy_ops.h", "_foreach_asin_ops.h", "adaptive_avg_pool1d_native.h", "_pdist_forward_ops.h", "native_dropout_native.h", "logical_xor_ops.h", "_test_optional_filled_intlist_ops.h", "unsqueeze_native.h", "error_messages.h", "allclose_native.h", "_use_cudnn_rnn_flatten_weight_native.h", "dense_dim_native.h", "quantize_per_tensor_ops.h", "_indices_copy_ops.h", "binary_cross_entropy_backward_native.h", "avg_pool2d_meta.h", "heaviside_ops.h", "upsample_linear1d_compositeimplicitautograd_dispatch.h", "_sparse_broadcast_to_native.h", "addmm_meta.h", "reflection_pad2d_ops.h", "triu_meta.h", "repeat_interleave_compositeimplicitautograd_dispatch.h", "q_per_channel_axis_ops.h", "_cast_Double_native.h", "throughput_benchmark.h", "special_gammaln.h", "addbmm_native.h", "special_bessel_y0_meta.h", "cumprod_compositeexplicitautogradnonfunctional_dispatch.h", "fft_ifft2.h", "out_types.h", "softshrink_backward.h", "bitwise_right_shift.h", "vsplit_native.h", "conv2d_compositeimplicitautograd_dispatch.h", "mm_native.h", "glu_backward.h", "as_strided_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_to_cpu.h", "sin.h", "_mps_convolution_ops.h", "trunc_meta.h", "addmm_ops.h", "native_batch_norm_backward.h", "Types.h", "_native_multi_head_attention.h", "mkldnn_adaptive_avg_pool2d_backward_native.h", "special_legendre_polynomial_p_ops.h", "output-archive.h", "mem_dependency_checker.h", "symbolic.h", "_amp_update_scale_ops.h", "fft_rfft2_ops.h", "autograd.h", "max_unpool3d.h", "_foreach_copy_native.h", "addmv_ops.h", "_autocast_to_full_precision_ops.h", "QnnpackUtils.h", "cosine_embedding_loss_native.h", "reflection_pad1d_ops.h", "serialize.h", "scatter_add_native.h", "EmptyTensor.h", "all_ops.h", "linalg_inv_ex.h", "block_diag_native.h", "_foreach_log2_ops.h", "linalg_eigvals.h", "comm.h", "poisson_native.h", "vec512_bfloat16.h", "source_ref.h", "_pad_circular_ops.h", "rand_like_native.h", "addmm.h", "copysign_ops.h", "_unique2.h", "pickle.h", "masked_select_backward.h", "adjoint_native.h", "TensorShape.h", "huber_loss_backward.h", "TensorIteratorDynamicCasting.h", "conv_transpose1d_ops.h", "Functions.h", "div_compositeexplicitautogradnonfunctional_dispatch.h", "var_mean_compositeimplicitautograd_dispatch.h", "_upsample_nearest_exact2d_meta.h", "arctan_native.h", "mv.h", "dropout.h", "unsafe_split_with_sizes_ops.h", "linalg_det_ops.h", "new_empty_native.h", "upsample_nearest2d_backward_meta.h", "logspace_native.h", "copysign_native.h", "conv1d_compositeimplicitautograd_dispatch.h", "can_cast_compositeimplicitautograd_dispatch.h", "mps_convolution_backward_ops.h", "instance_norm_native.h", "lshift.h", "split.h", "TraceUtils.h", "quantile_ops.h", "is_vulkan_available.h", "unflatten_dense_tensors_native.h", "Load.h", "binary_cross_entropy.h", "fractional_max_pool2d_ops.h", "python_resp.h", "log_normal_ops.h", "baddbmm.h", "_reshape_from_tensor_ops.h", "native_channel_shuffle_ops.h", "copy_native.h", "special_laguerre_polynomial_l_meta.h", "_assert_async_ops.h", "RNN.h", "histogram_cpu_dispatch.h", "exp2_meta.h", "lift_ops.h", "avg_pool2d_backward_ops.h", "isin_ops.h", "unfold.h", "stack.h", "ones_like.h", "_softmax.h", "python_compat.h", "conj_physical.h", "blackman_window_ops.h", "fft_ihfft2_ops.h", "_scaled_dot_product_efficient_attention_backward_ops.h", "_foreach_erf_native.h", "canonicalize_graph_fuser_ops.h", "index_copy_ops.h", "to_mkldnn_cpu_dispatch.h", "repeat_interleave.h", "BoxedKernel_impl.h", "upsample_linear1d.h", "broadcast_tensors_native.h", "repeat_interleave_cuda_dispatch.h", "special_expit_native.h", "view_as_complex_ops.h", "linalg_ldl_factor_native.h", "reciprocal_native.h", "base.h", "FunctionOfAMatrixUtils.h", "fliplr_native.h", "_cudnn_ctc_loss.h", "ger_ops.h", "_add_relu.h", "detach_native.h", "coalesce_native.h", "atanh_native.h", "_scaled_mm_cuda_dispatch.h", "PhiloxRNGEngine.h", "batch_norm_update_stats_ops.h", "sign_ops.h", "upsample_linear1d_meta_dispatch.h", "_foobar_native.h", "_cummax_helper_native.h", "grid_sampler_2d_ops.h", "cudnn_affine_grid_generator.h", "cholesky_ops.h", "fbgemm_pack_gemm_matrix_fp16_native.h", "_foreach_asin.h", "embed.h", "linalg_tensorinv.h", "CUDABlas.h", "TensorWrapper.h", "Reduction.h", "upsample_trilinear3d_backward.h", "reflection_pad1d_backward_meta.h", "_nested_tensor_softmax_with_shape_native.h", "adjoint_ops.h", "native_layer_norm_backward_ops.h", "Resize.h", "threshold_native.h", "bitwise_xor_meta.h", "CallOnce.h", "LaunchUtils.h", "sum.h", "adaptive_max_pool3d_backward.h", "util.h", "sgn.h", "row_indices_native.h", "special_log_softmax.h", "vec256_complex_double.h", "_convolution_compositeimplicitautograd_dispatch.h", "Copy.h", "pinverse.h", "DispatchKeySet.h", "_upsample_nearest_exact1d_meta_dispatch.h", "_to_sparse_csc_compositeexplicitautograd_dispatch.h", "arccos_native.h", "negative.h", "python_sugared_value.h", "nested_to_padded_tensor.h", "argmin_native.h", "VariableTypeUtils.h", "container.h", "native_channel_shuffle_native.h", "_upsample_nearest_exact1d_backward_cuda_dispatch.h", "stack.h", "_to_sparse_cuda_dispatch.h", "_convolution_double_backward_ops.h", "Parallel-inl.h", "randperm_cuda_dispatch.h", "fft_ifftn_ops.h", "_test_ambiguous_defaults.h", "abs_ops.h", "_upsample_bicubic2d_aa_backward_cpu_dispatch.h", "padding.h", "python_call.h", "nll_loss_ops.h", "python_tree_views.h", "_sparse_csc_tensor_unsafe.h", "Histogram.h", "custom_function.h", "_sparse_broadcast_to_copy_native.h", "_foreach_ceil_native.h", "new_ones_compositeexplicitautograd_dispatch.h", "_cast_Half_native.h", "upsample_nearest3d_backward_ops.h", "isreal_native.h", "_batch_norm_impl_index_compositeimplicitautograd_dispatch.h", "conv_transpose2d_native.h", "stft.h", "FuncTorchTLS.h", "replication_pad1d_ops.h", "special_round_ops.h", "lerp_native.h", "ExclusivelyOwned.h", "_foreach_sigmoid_ops.h", "_fill_mem_eff_dropout_mask_native.h", "_linalg_check_errors.h", "special_scaled_modified_bessel_k0_ops.h", "_sparse_softmax_backward_data_ops.h", "randperm_ops.h", "_amp_foreach_non_finite_check_and_unscale.h", "lstm_cell.h", "linalg_matrix_norm_native.h", "_nested_view_from_buffer_ops.h", "_histogramdd_from_bin_tensors.h", "_sparse_mm_reduce_impl_native.h", "jit_decomp_interface.h", "remainder_ops.h", "matmul_backward_native.h", "_to_dense.h", "conv2d_ops.h", "stateful.h", "_euclidean_dist.h", "_mps_convolution.h", "python_nested_functions.h", "group_norm.h", "tensor_layouts.h", "_cudnn_rnn_backward_native.h", "profiling_graph_executor_impl.h", "embedding_renorm.h", "resolve_conj_ops.h", "_fft_c2r_native.h", "conv_tbc_backward_ops.h", "_cdist_backward_ops.h", "request_callback.h", "special_spherical_bessel_j0_ops.h", "mse_loss_backward_native.h", "resize_native.h", "histogramdd_ops.h", "_backward_compositeimplicitautograd_dispatch.h", "upsample_nearest2d_backward_native.h", "index_add.h", "_foreach_neg_ops.h", "_nnz_native.h", "floor_native.h", "linspace_native.h", "_resize_output_native.h", "square.h", "softplus_meta.h", "_nested_from_padded_and_nested_example_ops.h", "view_as_complex_copy_ops.h", "strides.h", "set.h", "cuda.h", "linalg_diagonal.h", "linalg_ldl_solve_ops.h", "adaptive_avg_pool2d_ops.h", "select.h", "special_shifted_chebyshev_polynomial_u_native.h", "nll_loss_forward.h", "types.h", "copysign.h", "relu.h", "slow_conv3d_ops.h", "q_per_channel_scales.h", "special_legendre_polynomial_p_meta.h", "value_selecting_reduction_backward_ops.h", "_test_optional_intlist.h", "parser.h", "cholesky_inverse.h", "slice_copy_ops.h", "lr_scheduler.h", "_choose_qparams_per_tensor.h", "linalg_ldl_factor_ex_meta.h", "DeviceThreadHandles.h", "lstm_native.h", "exception.h", "conv_tbc_native.h", "slow_conv_transpose2d.h", "cummax_native.h", "quantized_rnn_tanh_cell_ops.h", "diag_embed.h", "t.h", "group_norm_native.h", "mse_loss_backward.h", "_local_scalar_dense_native.h", "cholesky_solve_native.h", "_linalg_eigh_native.h", "RedispatchFunctions.h", "affine_grid_generator.h", "unbind.h", "FunctionalStorageImpl.h", "thread_pool.h", "chalf.h", "mkldnn_rnn_layer_backward.h", "scalar_tensor.h", "logit.h", "LinearAlgebra.h", "view.h", "exception_message.h", "max_pool2d_backward_ops.h", "avg_pool1d.h", "vec512_float.h", "clone_ops.h", "as_strided_scatter.h", "diagflat_native.h", "embedding.h", "diag.h", "named_any.h", "StackKernel.h", "batch_norm_native.h", "_embedding_bag_cuda_dispatch.h", "index_select_native.h", "upsample_trilinear3d_cuda_dispatch.h", "_fill_mem_eff_dropout_mask.h", "gelu_backward.h", "as_strided_meta_dispatch.h", "_sparse_coo_tensor_with_dims_native.h", "binomial.h", "resize.h", "empty_cuda_dispatch.h", "RuyUtils.h", "soft_margin_loss_backward_ops.h", "pixel_unshuffle_ops.h", "avg_pool3d_backward_cpu_dispatch.h", "symbolic_shape_analysis.h", "ldexp_ops.h", "utf8_decoding_ignore.h", "reshape_as_ops.h", "triangular_solve_meta.h", "dense_dim.h", "types.h", "chalf_compositeimplicitautograd_dispatch.h", "to_mkldnn_ops.h", "cleanup_autograd_context_req.h", "upsample_bilinear2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_upsample_nearest_exact2d_native.h", "linalg_vector_norm_meta_dispatch.h", "avg_pool3d_cpu_dispatch.h", "dot_native.h", "cross_ops.h", "fbgemm_linear_quantize_weight_ops.h", "IndexKernel.h", "nansum_native.h", "fft_ifft.h", "_upsample_nearest_exact2d.h", "adaptive_avg_pool3d_native.h", "log_softmax_native.h", "linalg_ldl_factor_ex.h", "_foreach_floor_native.h", "bounds_overlap.h", "MatrixRef.h", "_indices_copy.h", "amax_ops.h", "tensordot_native.h", "svd_native.h", "div_cpu_dispatch.h", "nanmean_ops.h", "upsample_bicubic2d_backward_native.h", "q_scale.h", "rrelu_compositeimplicitautograd_dispatch.h", "sparse_csr_tensor_ops.h", "upsample_nearest3d_backward_cpu_dispatch.h", "create_functional_graphs.h", "nextafter_ops.h", "conv_transpose3d_compositeimplicitautograd_dispatch.h", "diagonal_scatter_native.h", "_upsample_bilinear2d_aa_backward_native.h", "index_copy_native.h", "logical_or.h", "utils.h", "special_zeta_ops.h", "cudnn_is_acceptable.h", "align_to_native.h", "_standard_gamma_cpu_dispatch.h", "nll_loss_compositeimplicitautograd_dispatch.h", "miopen_convolution_transpose_native.h", "logsumexp_ops.h", "linalg_pinv_compositeexplicitautogradnonfunctional_dispatch.h", "quantized_max_pool1d_native.h", "fold.h", "mH_ops.h", "log2.h", "events.h", "miopen_convolution_relu_native.h", "align_as.h", "linear_backward_ops.h", "_nested_tensor_strides_ops.h", "special_i0_ops.h", "erfc_meta.h", "scope.h", "special_chebyshev_polynomial_t_native.h", "fft_hfft2.h", "peephole_list_idioms.h", "upsample_bicubic2d_compositeexplicitautogradnonfunctional_dispatch.h", "from_file_ops.h", "_upsample_nearest_exact1d_backward_meta_dispatch.h", "matmul_backward_ops.h", "full.h", "_to_sparse_bsc.h", "randint_like.h", "miopen_convolution_add_relu.h", "deg2rad.h", "_lu_with_info.h", "native_group_norm_backward.h", "feature_dropout_native.h", "_test_functorch_fallback_ops.h", "fft_irfft2_compositeimplicitautograd_dispatch.h", "silu_ops.h", "sqrt_meta.h", "trapz.h", "absolute_native.h", "import.h", "select_copy_ops.h", "angle.h", "upsample_linear1d_compositeexplicitautogradnonfunctional_dispatch.h", "_local_scalar_dense.h", "batch_norm_update_stats_cpu_dispatch.h", "fft_fftshift.h", "_conv_depthwise2d_ops.h", "argmin_cpu_dispatch.h", "linalg_det.h", "KernelUtils.h", "cholesky_solve.h", "t_copy_native.h", "diagonal_backward_ops.h", "batch_norm_gather_stats_compositeexplicitautograd_dispatch.h", "batch_norm_elemt.h", "ADInterpreters.h", "IndexKernels.h", "mT_native.h", "linear.h", "random.h", "_histogramdd_from_bin_tensors_cpu_dispatch.h", "permute_copy_native.h", "linear.h", "Exception.h", "LazyNVRTC.h", "_cummin_helper_native.h", "special_modified_bessel_k1_meta.h", "reduction.h", "var_mean_cpu_dispatch.h", "norm_native.h", "interned_strings_class.h", "upsample_linear1d_meta.h", "C++17.h", "logit_ops.h", "loss.h", "_rowwise_prune_ops.h", "miopen_batch_norm_native.h", "frozen_linear_transpose.h", "linspace_compositeexplicitautograd_dispatch.h", "channel_shuffle.h", "convolution_backward_overrideable_native.h", "CPUFunctions_inl.h", "logit_backward_meta.h", "special_chebyshev_polynomial_v_ops.h", "amin_meta.h", "_foreach_addcdiv_ops.h", "lshift_native.h", "empty_strided_cuda_dispatch.h", "embedding_backward_native.h", "fold.h", "attributes.h", "IndexKernel.h", "_sparse_bsc_tensor_unsafe_compositeimplicitautograd_dispatch.h", "lstm_cell_compositeimplicitautograd_dispatch.h", "sequential.h", "max_pool3d_with_indices_backward_ops.h", "WrapDimUtilsMulti.h", "affine_grid_generator_ops.h", "_masked_softmax_cpu_dispatch.h", "sparse_compressed_tensor_native.h", "variable.h", "smm.h", "SpectralOpsUtils.h", "fft_rfftfreq.h", "_foreach_atan_ops.h", "CPUFixedAllocator.h", "dlpack.h", "geometric.h", "index_put_ops.h", "is_vulkan_available_ops.h", "im2col.h", "_upsample_nearest_exact1d_native.h", "embedding_ops.h", "MPSGeneratorImpl.h", "_sparse_addmm.h", "_convert_indices_from_coo_to_csr.h", "matrix_power.h", "_embedding_bag_forward_only_ops.h", "slice_scatter_compositeexplicitautograd_dispatch.h", "div_meta.h", "_log_softmax.h", "_cast_Long.h", "upsample_nearest1d_cpu_dispatch.h", "cauchy_ops.h", "alias_copy_ops.h", "to_sparse_bsc_ops.h", "linalg_cholesky_native.h", "special_bessel_j0.h", "special_entr_ops.h", "pad_sequence_compositeimplicitautograd_dispatch.h", "linalg_eigvalsh_native.h", "binomial_cuda_dispatch.h", "_grid_sampler_2d_cpu_fallback_backward_native.h", "new_ones_ops.h", "resize_cuda_dispatch.h", "round_meta.h", "reciprocal_ops.h", "nested.h", "_mkldnn_reshape_ops.h", "hinge_embedding_loss.h", "tile_native.h", "norm_compositeimplicitautograd_dispatch.h", "cudnn_batch_norm_backward_compositeexplicitautograd_dispatch.h", "_triton_multi_head_attention_cuda_dispatch.h", "instancenorm.h", "Float8_e5m2-inl.h", "conv1d_native.h", "hspmm.h", "_prelu_kernel_backward_ops.h", "_upsample_nearest_exact3d_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_w.h", "nll_loss_nd_compositeimplicitautograd_dispatch.h", "ceil_ops.h", "_sparse_semi_structured_linear.h", "TensorOptions.h", "_embedding_bag_dense_backward_cpu_dispatch.h", "_foobar.h", "quantile_compositeimplicitautograd_dispatch.h", "CUDAGuardImpl.h", "_saturate_weight_to_fp16.h", "linalg_matrix_norm_ops.h", "_native_batch_norm_legit_no_training_compositeexplicitautograd_dispatch.h", "special_modified_bessel_i0_meta.h", "parser_constants.h", "_cast_Int_ops.h", "itt_wrapper.h", "pixel_shuffle_ops.h", "common_subexpression_elimination.h", "DistributionsHelper.h", "_native_batch_norm_legit_cpu_dispatch.h", "base.h", "_scaled_dot_product_efficient_attention_ops.h", "norm_compositeexplicitautograd_dispatch.h", "einsum_ops.h", "chalf_ops.h", "fused_moving_avg_obs_fake_quant_ops.h", "OperatorEntry.h", "expand_as.h", "IndexKernel.h", "activation.h", "clip_grad.h", "Parallel.h", "affine_grid_generator_backward.h", "debug_util.h", "hamming_window_native.h", "embedding_renorm_ops.h", "CUDAEvent.h", "_foreach_tanh.h", "cumsum_compositeimplicitautograd_dispatch.h", "ravel.h", "PeerToPeerAccess.h", "embedding_sparse_backward_ops.h", "_sparse_mask_projection.h", "poisson.h", "upsample_linear1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_unique.h", "silu_native.h", "bitwise_xor_native.h", "cat_meta.h", "_sobol_engine_initialize_state_ops.h", "fractional_max_pool3d.h", "_dirichlet_grad.h", "logaddexp_native.h", "item_native.h", "_test_optional_filled_intlist_native.h", "_sparse_csr_tensor_unsafe_compositeimplicitautograd_dispatch.h", "smm_ops.h", "as_strided_ops.h", "slow_conv_dilated2d_cpu_dispatch.h", "_embedding_bag_per_sample_weights_backward_ops.h", "isneginf.h", "_fake_quantize_learnable_per_channel_affine.h", "ScalarOps.h", "buffer_info.h", "fft_ifftshift_ops.h", "searchsorted_native.h", "mode.h", "polygamma.h", "batch_norm_elemt_native.h", "_add_relu_native.h", "symbolic_shape_registry.h", "_transform_bias_rescale_qkv_native.h", "ir_metadata.h", "special_bessel_y1.h", "fusion_passes.h", "quantized_max_pool2d_native.h", "_embedding_bag_forward_only_native.h", "log_sigmoid_backward_ops.h", "flipud_ops.h", "VmapInterpreter.h", "fft_fftn.h", "_scaled_dot_product_attention_math_native.h", "fbgemm_pack_quantized_matrix_ops.h", "argmax.h", "add_native.h", "quantize_per_tensor_dynamic_native.h", "logit_meta_dispatch.h", "vec256_complex_double_vsx.h", "_sobol_engine_scramble.h", "norm_meta_dispatch.h", "_test_functorch_fallback.h", "convolution_native.h", "saved_variable_hooks.h", "var_mean_ops.h", "segment_reduce.h", "quantized_batch_norm_native.h", "Stream.h", "stream.h", "transpose_copy_native.h", "_foreach_expm1.h", "linalg_lu_factor_ex_ops.h", "is_leaf.h", "swapdims.h", "grad_mode.h", "sparse_coo_tensor_compositeexplicitautograd_dispatch.h", "asinh_native.h", "threshold_backward.h", "cosine_embedding_loss.h", "unsafe_chunk_native.h", "quantized_lstm_cell_native.h", "ts_lowering_context.h", "_masked_softmax_compositeexplicitautograd_dispatch.h", "poisson_nll_loss.h", "backend_debug_info.h", "copy_sparse_to_sparse_native.h", "slow_conv_transpose2d_meta.h", "pinverse_ops.h", "_nnpack_available_ops.h", "_saturate_weight_to_fp16_ops.h", "squeeze_copy.h", "_coalesced_ops.h", "to_compositeimplicitautograd_dispatch.h", "_foreach_log_native.h", "fft_ihfft2_native.h", "Logging.h", "_sparse_bsr_tensor_unsafe_ops.h", "comm.h", "special_i0_native.h", "lstm_ops.h", "leaky_relu_backward_native.h", "asinh.h", "fft_rfft.h", "sparse_coo_tensor.h", "builtin_function.h", "multi_margin_loss_cpu_dispatch.h", "int_repr_native.h", "Descriptors.h", "BoxedKernel.h", "arctan_ops.h", "rrelu_native.h", "zeros_like.h", "exponential_cuda_dispatch.h", "_is_zerotensor_native.h", "logit_backward_native.h", "utils.h", "signbit_ops.h", "nonzero.h", "distance.h", "matrix_exp_ops.h", "argument_spec.h", "signbit_native.h", "mean_meta_dispatch.h", "is_vulkan_available_native.h", "_to_sparse_bsr.h", "split_with_sizes_ops.h", "fix.h", "fft_irfftn_native.h", "_upsample_nearest_exact2d_cpu_dispatch.h", "positive_native.h", "segment_reduce_compositeexplicitautograd_dispatch.h", "q_per_channel_axis.h", "randn_compositeimplicitautograd_dispatch.h", "ir_dump_util.h", "_unsafe_index_put_compositeexplicitautograd_dispatch.h", "cudnn_convolution_add_relu_ops.h", "Lerp.h", "_foreach_asin_native.h", "igamma_native.h", "is_same_size.h", "_scaled_dot_product_attention_math_ops.h", "cross_native.h", "_pad_packed_sequence_native.h", "digamma.h", "digamma_native.h", "binary_cross_entropy_with_logits.h", "_to_sparse_semi_structured.h", "metal_rewrite.h", "masked_fill.h", "rnn_relu.h", "NativeFunctions.h", "_trilinear_native.h", "linalg_lstsq_cuda_dispatch.h", "_nnpack_spatial_convolution_ops.h", "_stack_ops.h", "mkldnn_max_pool2d.h", "_cslt_compress.h", "rename_native.h", "linalg_solve.h", "fractional_max_pool3d_backward_native.h", "_linalg_svd_ops.h", "special_i1e_native.h", "sum_meta_dispatch.h", "max_pool2d_native.h", "rref_backward_resp.h", "polar_native.h", "reciprocal.h", "celu.h", "trapezoid_native.h", "ceil.h", "conj.h", "TypeSafeSignMath.h", "_to_sparse_bsc_compositeexplicitautograd_dispatch.h", "constant_propagation.h", "upsample_nearest2d_ops.h", "_foreach_maximum_ops.h", "_flash_attention_backward_ops.h", "acosh.h", "quantization.h", "dropout_native.h", "cudnn_batch_norm_compositeexplicitautograd_dispatch.h", "python_saved_variable_hooks.h", "_softmax_meta.h", "stride_ops.h", "ScatterGatherChecks.h", "special_modified_bessel_k0_ops.h", "upsample_nearest2d_backward_cpu_dispatch.h", "_to_sparse_bsr_compositeexplicitautograd_dispatch.h", "glu_jvp_ops.h", "trunc_native.h", "quantization.h", "_fake_quantize_learnable_per_tensor_affine_backward.h", "gradient.h", "hardsigmoid_backward.h", "softshrink.h", "rsqrt_meta.h", "special_modified_bessel_k0.h", "BatchLinearAlgebra.h", "_foobar_ops.h", "_histogramdd_from_bin_tensors_compositeexplicitautograd_dispatch.h", "logging_is_not_google_glog.h", "_sparse_log_softmax.h", "profiler_legacy.h", "_sparse_addmm_native.h", "_sparse_broadcast_to.h", "adagrad.h", "linalg_tensorinv_ops.h", "log1p_ops.h", "diagonal_backward.h", "function_schema_parser.h", "pixel_shuffle_native.h", "rename_ops.h", "argmin_meta.h", "fake_quantize_per_channel_affine_cachemask.h", "linalg_eigvals_native.h", "quantized_rnn_tanh_cell_native.h", "decomposition_registry_util.h", "nll_loss_forward_native.h", "perf.h", "cov_ops.h", "bartlett_window_ops.h", "builtin_functions.h", "logaddexp.h", "_nested_from_padded_ops.h", "leaky_relu_meta.h", "addcdiv_meta.h", "new_empty_strided_ops.h", "custom_batch_request.h", "mkldnn_rewrite.h", "SparseTensorImpl.h", "chunk_ops.h", "new_empty.h", "upsample_trilinear3d_compositeimplicitautograd_dispatch.h", "sum_compositeexplicitautograd_dispatch.h", "linalg_eigvals_ops.h", "log_sigmoid_forward_ops.h", "cudnn_convolution_relu_compositeexplicitautograd_dispatch.h", "TensorConversions.h", "interface.h", "scalar_tensor_compositeexplicitautograd_dispatch.h", "atan_ops.h", "linalg_ldl_factor_ops.h", "test_helpers.h", "sspaddmm.h", "avg_pool3d_ops.h", "cummaxmin_backward_ops.h", "values_copy_ops.h", "permutation_util.h", "instancenorm.h", "_upsample_nearest_exact3d_backward_meta_dispatch.h", "_flash_attention_forward_ops.h", "special_i1e_meta.h", "_sparse_broadcast_to_ops.h", "one_hot_native.h", "cummax_ops.h", "special_modified_bessel_k0_meta.h", "interpreter.h", "quantized_batch_norm_compositeexplicitautograd_dispatch.h", "randint_compositeexplicitautograd_dispatch.h", "_test_autograd_multiple_dispatch_native.h", "_convert_indices_from_coo_to_csr_meta.h", "concat.h", "unbind_native.h", "mean_cuda_dispatch.h", "rand_compositeimplicitautograd_dispatch.h", "_foreach_tanh_native.h", "upsample_bicubic2d.h", "arccos.h", "adaptive_max_pool2d_ops.h", "special_ndtr_native.h", "upsample_bicubic2d_meta_dispatch.h", "binary_cross_entropy_native.h", "avg_pool1d_ops.h", "argmax_cuda_dispatch.h", "sparse_bsr_tensor_compositeimplicitautograd_dispatch.h", "_make_per_channel_quantized_tensor.h", "arange_native.h", "_fused_sdp_choice_native.h", "margin_ranking_loss_ops.h", "_upsample_bilinear2d_aa_meta_dispatch.h", "_cast_Int.h", "miopen_convolution_relu_ops.h", "linalg_lstsq_ops.h", "linalg_vector_norm_ops.h", "autograd_not_implemented_fallback.h", "fft_fftshift_ops.h", "empty_cpu_dispatch.h", "_fused_sdp_choice_ops.h", "_convolution_double_backward_compositeimplicitautograd_dispatch.h", "dequantize_ops.h", "_make_per_channel_quantized_tensor_ops.h", "linalg_lstsq_compositeexplicitautograd_dispatch.h", "erfinv_ops.h", "linalg_cond_native.h", "broadcast_to.h", "InferSize.h", "nanmedian_ops.h", "mnist.h", "max_pool3d_with_indices_ops.h", "special_airy_ai.h", "VariableHooksInterface.h", "CUDASparse.h", "combinations_ops.h", "_upsample_nearest_exact3d_compositeimplicitautograd_dispatch.h", "_weight_norm_ops.h", "_cast_Float.h", "TensorAccessor.h", "_scaled_dot_product_flash_attention_backward_native.h", "as_strided_compositeexplicitautogradnonfunctional_dispatch.h", "fbgemm_linear_int8_weight_fp32_activation_ops.h", "linalg_solve_triangular.h", "addmm_native.h", "_foreach_pow.h", "LossMulti.h", "_embedding_bag_sparse_backward_ops.h", "_nested_from_padded.h", "_cast_Char.h", "common.h", "l1_loss_native.h", "_nested_tensor_from_tensor_list_native.h", "slow_conv_transpose2d_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_log_softmax_native.h", "mish_backward.h", "linalg_vecdot_native.h", "linalg_lu_factor_ex_meta.h", "var_mean_native.h", "python_raii.h", "quantized_rnn_tanh_cell.h", "convolution.h", "quantized_gru_cell.h", "elu_backward_meta.h", "_foreach_mul.h", "istft_compositeimplicitautograd_dispatch.h", "max_native.h", "bmm_native.h", "chain_matmul_native.h", "special_modified_bessel_k1_ops.h", "ir_verifier.h", "unsafe_split_ops.h", "linalg_vector_norm_compositeexplicitautogradnonfunctional_dispatch.h", "api.h", "_fused_dropout_compositeexplicitautograd_dispatch.h", "remove_exceptions.h", "fill_native.h", "special_i1_native.h", "less.h", "_foreach_pow_ops.h", "_foreach_atan.h", "_fake_quantize_learnable_per_channel_affine_backward.h", "any.h", "_slow_conv2d_forward.h", "randint_ops.h", "saved_variable.h", "special_softmax_compositeimplicitautograd_dispatch.h", "cuda_enabled.h", "_indices_native.h", "linalg_pinv_ops.h", "_native_batch_norm_legit_compositeexplicitautograd_dispatch.h", "randn_ops.h", "_fw_primal_copy_ops.h", "Float8_e4m3fn.h", "_dimV.h", "_cudnn_init_dropout_state_cuda_dispatch.h", "scatter_add.h", "exp2.h", "smooth_l1_loss_backward.h", "Copy.h", "Reduce.h", "Distance.h", "neg.h", "upsample_nearest3d_ops.h", "isfinite.h", "_flash_attention_backward_native.h", "dataloader.h", "unfold_backward.h", "norm_compositeexplicitautogradnonfunctional_dispatch.h", "arccosh_ops.h", "Factory.h", "upsample_nearest1d.h", "_test_autograd_multiple_dispatch_view_native.h", "function_hook.h", "swapaxes_native.h", "native_dropout_backward.h", "_sparse_softmax.h", "log10_meta.h", "slow_conv_dilated2d_cuda_dispatch.h", "sparse_sampled_addmm_ops.h", "backend_device.h", "diagonal_scatter_ops.h", "is_distributed.h", "miopen_rnn_backward_compositeexplicitautograd_dispatch.h", "Device.h", "pybind.h", "_log_softmax_backward_data_native.h", "_embedding_bag_sparse_backward_compositeimplicitautograd_dispatch.h", "q_zero_point_native.h", "neg_ops.h", "_batch_norm_impl_index.h", "config.h", "Optional.h", "gelu.h", "_fw_primal.h", "helpers.h", "bilinear_ops.h", "_cudnn_init_dropout_state_ops.h", "analysis.h", "tan.h", "distance.h", "moveaxis_ops.h", "native_group_norm_compositeexplicitautograd_dispatch.h", "infinitely_differentiable_gelu_backward_ops.h", "fbgemm_linear_fp16_weight_native.h", "floor_divide_ops.h", "slow_conv_transpose3d_cuda_dispatch.h", "argmin_cuda_dispatch.h", "Repeat.h", "scatter_reduce_native.h", "split_ops.h", "_linalg_slogdet.h", "slow_conv_transpose2d_ops.h", "TensorTransformations.h", "upsample_nearest3d_backward_meta_dispatch.h", "svd.h", "isreal.h", "GridSamplerKernel.h", "einsum_compositeimplicitautograd_dispatch.h", "atleast_3d_native.h", "logging.h", "cudnn_grid_sampler.h", "byte_order.h", "repeat_ops.h", "ones_like_native.h", "narrow_copy_native.h", "unfold_backward_native.h", "registerizer.h", "_sparse_csr_prod_compositeexplicitautograd_dispatch.h", "fix_ops.h", "_convolution_mode_native.h", "sparse_csr_tensor_compositeimplicitautograd_dispatch.h", "_test_string_default_ops.h", "randn_like_ops.h", "code.h", "_prelu_kernel_ops.h", "_sparse_csr_sum_compositeexplicitautograd_dispatch.h", "requires_grad.h", "narrow.h", "_validate_sparse_csc_tensor_args_ops.h", "_batch_norm_impl_index_native.h", "addcmul_ops.h", "_foreach_log1p.h", "upsample_trilinear3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "python_autograd.h", "kthvalue.h", "QEngine.h", "transformer.h", "_make_per_tensor_quantized_tensor_native.h", "mean_compositeimplicitautograd_dispatch.h", "_conj.h", "sgd.h", "normal_compositeexplicitautograd_dispatch.h", "Scalar.h", "_use_cudnn_rnn_flatten_weight_ops.h", "slow_conv_transpose3d_native.h", "unbind_copy_native.h", "log10_native.h", "expand_copy.h", "fmod_meta.h", "_test_string_default.h", "fake_quantize_per_channel_affine_cachemask_backward_native.h", "_test_string_default_native.h", "remainder.h", "real_native.h", "script_profile.h", "tempfile.h", "python_remote_call.h", "sub.h", "any_ops.h", "fill_diagonal.h", "_foreach_mul_ops.h", "TensorBase.h", "_rowwise_prune_native.h", "_flash_attention_backward_cuda_dispatch.h", "multinomial_ops.h", "schema_info.h", "is_set_to_native.h", "TypeCast.h", "nan_to_num_native.h", "isfinite_native.h", "tril_meta.h", "linalg_matrix_rank_compositeimplicitautograd_dispatch.h", "sparse_dim.h", "parameterlist.h", "liveness.h", "trapz_ops.h", "quantized_gru_cell_native.h", "embedding_dense_backward_ops.h", "logical_or_ops.h", "linalg_vander_ops.h", "cudnn_convolution_relu_native.h", "alias_native.h", "upsample_trilinear3d_native.h", "from_file_compositeexplicitautograd_dispatch.h", "empty_meta_dispatch.h", "DeadlockDetection.h", "log_normal.h", "record_stream_ops.h", "std_ops.h", "is_inference.h", "throughput_benchmark-inl.h", "not_equal_native.h", "segment_reduce_ops.h", "softshrink_meta.h", "erf_native.h", "adaptive.h", "_embedding_bag_sparse_backward_native.h", "_masked_softmax_backward_cuda_dispatch.h", "chunk_native.h", "_cast_Half.h", "BatchedTensorImpl.h", "new_ones.h", "fft_rfft2_native.h", "view_copy_ops.h", "is_floating_point.h", "nanmean_compositeimplicitautograd_dispatch.h", "flatten.h", "_sparse_coo_tensor_unsafe_compositeimplicitautograd_dispatch.h", "_assert_tensor_metadata_ops.h", "empty_like_ops.h", "eq_native.h", "_foreach_log1p_native.h", "quantize_per_channel_ops.h", "loss.h", "tensor_new.h", "linalg_det_native.h", "rsqrt_native.h", "sigmoid_ops.h", "hspmm_ops.h", "rand.h", "ReduceUtils.h", "init.h", "not_equal_ops.h", "init.h", "diagonal_ops.h", "zero_ops.h", "miopen_batch_norm_backward.h", "to_padded_tensor_compositeexplicitautograd_dispatch.h", "inner.h", "_fused_moving_avg_obs_fq_helper.h", "split_with_sizes_copy.h", "matrix_H_ops.h", "Config.h", "_upsample_bicubic2d_aa_backward_meta.h", "_thnn_fused_gru_cell_backward.h", "cauchy_native.h", "movedim_native.h", "result_type.h", "containers.h", "CUDAGeneratorImpl.h", "matrix.h", "cub.h", "_test_optional_floatlist_ops.h", "softplus.h", "linalg_ldl_solve_native.h", "heaviside_native.h", "ts_backend_impl.h", "_to_sparse_csc_ops.h", "bitwise_xor_ops.h", "_foreach_cosh_native.h", "rename_compositeimplicitautograd_dispatch.h", "special_modified_bessel_k0_native.h", "HermeticPyObjectTLS.h", "linalg_lu_solve_meta.h", "_cudnn_rnn_flatten_weight_ops.h", "rsub_ops.h", "cudnn_affine_grid_generator_backward_native.h", "_make_per_tensor_quantized_tensor.h", "basic_ops.h", "slice.h", "py_rref.h", "ones_ops.h", "bincount_compositeexplicitautograd_dispatch.h", "cpuinfo.h", "_autocast_to_reduced_precision.h", "prod_compositeexplicitautogradnonfunctional_dispatch.h", "contiguous_native.h", "config.h", "norm_except_dim_ops.h", "upsample_bicubic2d_backward_meta.h", "scatter_meta.h", "avg_pool2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "tensorexpr_init.h", "native_dropout_backward_ops.h", "_upsample_nearest_exact2d_compositeimplicitautograd_dispatch.h", "index_cpu_dispatch.h", "diag_embed_native.h", "embedding.h", "and.h", "special_xlogy_ops.h", "sub_native.h", "WrapFunctionIntoFunctor.h", "upsampling.h", "_use_cudnn_ctc_loss_native.h", "mm_ops.h", "floor_ops.h", "any_meta.h", "log2_native.h", "cummin_ops.h", "CPUBlas.h", "chunk.h", "zeros_like_native.h", "_dimI_ops.h", "_standard_gamma_ops.h", "sin_meta.h", "Module.h", "random_native.h", "argmin.h", "_cummin_helper.h", "_foreach_div_ops.h", "all.h", "_efficientzerotensor_cuda_dispatch.h", "_is_any_true.h", "reflection_pad3d_native.h", "linalg_eigvals_compositeimplicitautograd_dispatch.h", "_sparse_mask_projection_native.h", "matrix_exp_backward_ops.h", "quantization_type.h", "_use_cudnn_rnn_flatten_weight.h", "special_spherical_bessel_j0.h", "log_sigmoid_native.h", "index_add_meta.h", "_addmm_activation_native.h", "trace_backward_native.h", "_thnn_fused_lstm_cell_backward_impl_compositeexplicitautograd_dispatch.h", "complex_ops.h", "CppSignature.h", "conv_tbc_backward.h", "LegacyVmapMode.h", "slow_conv3d_forward_native.h", "linalg_cross_meta.h", "ormqr_ops.h", "CUDADeviceAssertion.h", "_cast_Long_native.h", "elu_meta.h", "native_layer_norm_backward.h", "fft_ihfft_ops.h", "native_batch_norm_cuda_dispatch.h", "ts_autograd_functions.h", "gcd_native.h", "_conj_ops.h", "source_range.h", "col_indices_copy_ops.h", "_assert_tensor_metadata_native.h", "_autocast_to_full_precision_native.h", "_foreach_frac.h", "miopen_rnn_backward.h", "resource_guard.h", "rpc_agent.h", "lower_graph.h", "linalg_cross_ops.h", "swapaxes_ops.h", "_foreach_sign.h", "zeros_compositeexplicitautograd_dispatch.h", "crow_indices_copy_native.h", "VirtualGuardImpl.h", "_cholesky_solve_helper_native.h", "cuda_random.h", "max_pool1d_with_indices.h", "hypot.h", "_segment_reduce_backward_cuda_dispatch.h", "mv_ops.h", "_embedding_bag_sparse_backward.h", "Flags.h", "vision.h", "indices_copy_ops.h", "_upsample_nearest_exact3d_meta.h", "check_alias_annotation.h", "linalg_matrix_power.h", "_neg_view_copy_native.h", "_efficientzerotensor_cpu_dispatch.h", "static_tracepoint_elfx86.h", "_sparse_csr_sum_native.h", "linalg_matrix_rank_ops.h", "logical_not_ops.h", "avg_pool2d_compositeexplicitautogradnonfunctional_dispatch.h", "ir.h", "_sparse_coo_tensor_with_dims_meta_dispatch.h", "LegacyVmapTransforms.h", "expm1_meta.h", "diagonal_native.h", "nll_loss_forward_cpu_dispatch.h", "adaptive_avg_pool3d_ops.h", "type_as.h", "resize_as_native.h", "codegen.h", "q_per_channel_zero_points_native.h", "std_mean_compositeimplicitautograd_dispatch.h", "_cudnn_rnn_native.h", "native_group_norm_backward_compositeexplicitautograd_dispatch.h", "randint.h", "sym_numel_native.h", "rrelu_with_noise_backward_ops.h", "stateful.h", "_to_sparse_compositeexplicitautograd_dispatch.h", "pytypes.h", "ccol_indices_copy.h", "hsplit.h", "_version_ops.h", "im2col.h", "xor_native.h", "MPSGraphVenturaOps.h", "sym_size_ops.h", "special_psi.h", "_to_sparse_bsr_cuda_dispatch.h", "_rowwise_prune.h", "linalg_eigvalsh_ops.h", "rref_proto.h", "nll_loss_native.h", "sendrpc_backward.h", "_pad_packed_sequence.h", "div_native.h", "addcmul_native.h", "native_norm_native.h", "CudaIPCTypes.h", "modulelist.h", "var_ops.h", "functional.h", "_masked_softmax_native.h", "_triton_multi_head_attention_compositeexplicitautograd_dispatch.h", "block_codegen.h", "ReductionType.h", "grad_layout_contract.h", "_grid_sampler_2d_cpu_fallback_ops.h", "unsafe_split_native.h", "triu_indices.h", "take_along_dim.h", "_make_dep_token_ops.h", "float_power_ops.h", "transformerlayer.h", "unfold_copy_native.h", "embedding_native.h", "miopen_convolution_compositeexplicitautograd_dispatch.h", "_efficient_attention_forward_native.h", "resize_as_compositeexplicitautograd_dispatch.h", "hardswish.h", "_aminmax.h", "meshgrid.h", "jit_opt_limit.h", "set_native.h", "dynamic_ir.h", "relu_native.h", "_validate_sparse_csc_tensor_args.h", "llvm_jit.h", "expm1_ops.h", "kaiser_window_compositeexplicitautograd_dispatch.h", "_empty_affine_quantized_cpu_dispatch.h", "_validate_compressed_sparse_indices.h", "type_hashing.h", "norm_cuda_dispatch.h", "fractional_max_pool2d_backward_ops.h", "nanquantile.h", "CUDAHooksInterface.h", "miopen_convolution_transpose.h", "grid_sampler_2d.h", "set_data.h", "fuse_linear.h", "reduce_on_plateau_scheduler.h", "is_coalesced_ops.h", "split_with_sizes_copy_ops.h", "hardtanh_backward_ops.h", "glu_backward_native.h", "special_gammaln_ops.h", "fuse_relu.h", "export.h", "bitwise_and.h", "lu_unpack_meta.h", "special_modified_bessel_k1_native.h", "expand_native.h", "logical_xor.h", "bitwise_left_shift_native.h", "GridSampler.h", "CuFFTUtils.h", "mH_native.h", "linalg_matrix_power_ops.h", "TensorSubclassLikeUtils.h", "align_tensors.h", "rpc_with_profiling_req.h", "rad2deg.h", "DeprecatedTypeProperties.h", "_sparse_log_softmax_compositeimplicitautograd_dispatch.h", "clip_native.h", "_fft_c2r_ops.h", "histogram_native.h", "_validate_sparse_compressed_tensor_args.h", "lstm_mps_backward_compositeexplicitautograd_dispatch.h", "autocast.h", "_spdiags_ops.h", "data.h", "upsample_bilinear2d_compositeexplicitautogradnonfunctional_dispatch.h", "argmax_cpu_dispatch.h", "ParallelOpenMP.h", "upsample_linear1d_backward_meta_dispatch.h", "_pad_enum_compositeimplicitautograd_dispatch.h", "fft_ihfft2_compositeimplicitautograd_dispatch.h", "_pack_padded_sequence.h", "empty_strided_cpu_dispatch.h", "trace_native.h", "_thnn_fused_gru_cell.h", "grid_sampler_3d_backward.h", "true_divide_native.h", "_amp_update_scale.h", "_values_copy_native.h", "addcdiv.h", "log2_ops.h", "unique_dim.h", "special_gammaincc_ops.h", "dynamic_type.h", "infer_schema.h", "propagate_gradients_req.h", "_foreach_minimum.h", "CachingHostAllocator.h", "zeros_native.h", "parameterdict.h", "subtract.h", "pimpl-inl.h", "inverse_native.h", "instancenorm.h", "amin.h", "empty.h", "avg_pool3d_backward_cuda_dispatch.h", "and_ops.h", "_dim_arange_ops.h", "pin_memory_ops.h", "TensorIterator.h", "adaptive_avg_pool3d_backward_ops.h", "linalg_lu_factor_ex.h", "multi_margin_loss_cuda_dispatch.h", "vsx_helpers.h", "_dim_arange_native.h", "slice_scatter_ops.h", "ReduceOpsUtils.h", "linalg_slogdet_ops.h", "tensorexpr_fuser.h", "Pool.h", "batch_norm_backward_reduce_compositeexplicitautograd_dispatch.h", "batch_norm_gather_stats_native.h", "fbgemm_linear_quantize_weight.h", "gru_cell_compositeimplicitautograd_dispatch.h", "linalg_matrix_rank_native.h", "IListRef.h", "_foreach_sign_ops.h", "fft_hfft_native.h", "nll_loss2d.h", "_ctc_loss_ops.h", "_empty_per_channel_affine_quantized.h", "softshrink_ops.h", "hsplit_ops.h", "python_tuples.h", "_embedding_bag_dense_backward_compositeexplicitautograd_dispatch.h", "_upsample_nearest_exact3d_backward_ops.h", "_unsafe_index_put_native.h", "_foreach_lerp_native.h", "take_native.h", "expand.h", "_scaled_mm_native.h", "_upsample_bicubic2d_aa_backward_compositeexplicitautogradnonfunctional_dispatch.h", "method.h", "complex_native.h", "_upsample_bicubic2d_aa_backward_native.h", "hardsigmoid_meta.h", "numpy.h", "_masked_softmax_backward.h", "imag_ops.h", "special_ndtr_ops.h", "addcdiv_ops.h", "CUDAAlgorithm.h", "nll_loss2d_backward_ops.h", "_fake_quantize_learnable_per_tensor_affine.h", "mkldnn_adaptive_avg_pool2d_backward_ops.h", "hardshrink_native.h", "native_group_norm_native.h", "as_strided_scatter_native.h", "max_pool3d_with_indices_native.h", "geqrf_native.h", "_nested_sum_backward_native.h", "fbgemm_linear_int8_weight_ops.h", "native_group_norm_cpu_dispatch.h", "alpha_dropout_native.h", "flatten_dense_tensors_ops.h", "Math.h", "tan_native.h", "input_buffer.h", "mkldnn_linear_backward.h", "uniform.h", "UndefinedTensorImpl.h", "NativeFunctions.h", "ravel_ops.h", "is_floating_point_native.h", "gru_native.h", "Array.h", "range_ops.h", "_euclidean_dist_native.h", "_compute_linear_combination.h", "_upsample_nearest_exact1d_backward_native.h", "sequencers.h", "fft_ihfftn_native.h", "_cast_Char_ops.h", "_unsafe_index_put.h", "bincount_ops.h", "_upsample_nearest_exact2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_make_dep_token_cpu_dispatch.h", "rref_context.h", "vec256_complex_float_vsx.h", "leaky_relu_backward_meta.h", "linalg_pinv_compositeimplicitautograd_dispatch.h", "cosine_similarity.h", "mkldnn_linear_backward_input.h", "permute_copy.h", "multinomial.h", "multinomial_cpu_dispatch.h", "tril_native.h", "unflatten_dense_tensors.h", "avg_pool2d_ops.h", "floor.h", "_lstm_mps_native.h", "_shape_as_tensor.h", "normalization.h", "frozen_linear_folding.h", "upsample_bilinear2d_backward_meta_dispatch.h", "full_native.h", "FunctionalTensorWrapper.h", "replication_pad2d_backward_ops.h", "special_i0.h", "TensorDimApply.h", "_weight_norm_differentiable_backward_ops.h", "special_modified_bessel_i0_native.h", "remove_redundant_profiles.h", "clamp_meta.h", "mkldnn_linear_backward_weights_native.h", "std_cuda_dispatch.h", "_test_serialization_subcmul_native.h", "special_log1p.h", "_cslt_sparse_mm_ops.h", "copy_sparse_to_sparse_ops.h", "mish_backward_ops.h", "_empty_affine_quantized_native.h", "cudnn_batch_norm.h", "_scaled_mm.h", "_make_dual.h", "special_gammaln_native.h", "linalg_qr.h", "WeightNormKernel.h", "IndexKernelUtils.h", "expand_ops.h", "Dispatch.h", "cudnn_batch_norm_native.h", "_reshape_copy.h", "feature_alpha_dropout.h", "clamp.h", "feature_dropout.h", "retains_grad_native.h", "histc.h", "_pad_enum.h", "fake_quantize_per_channel_affine_cachemask_ops.h", "upsample_trilinear3d.h", "linalg_householder_product.h", "hash.h", "baddbmm_native.h", "max_pool2d_with_indices_native.h", "binomial_native.h", "nll_loss_backward_meta_dispatch.h", "_trilinear.h", "native_batch_norm_backward_cpu_dispatch.h", "pin_memory.h", "div_meta_dispatch.h", "_native_batch_norm_legit_no_training_native.h", "masked_select_ops.h", "_fw_primal_native.h", "flatten_dense_tensors.h", "isposinf.h", "q_zero_point_ops.h", "swapdims_native.h", "linalg_lu_native.h", "lowering_context.h", "SharedReduceOps.h", "slice_copy_native.h", "sparse_bsr_tensor.h", "vision.h", "abs.h", "upsample_linear1d_backward_native.h", "batch_norm_backward_elemt.h", "_test_functorch_fallback_native.h", "row_indices.h", "TensorImpl.h", "_assert_async_native.h", "replication_pad2d_ops.h", "sym_size_native.h", "nll_loss_backward_ops.h", "absolute.h", "_cufft_get_plan_cache_size.h", "exponential_meta_dispatch.h", "_to_sparse_bsc_ops.h", "refine_tuple_types.h", "mul_meta.h", "DistributionTemplates.h", "unsqueeze_ops.h", "logit_backward_cuda_dispatch.h", "linalg_svd_ops.h", "_cholesky_solve_helper.h", "stft_ops.h", "einsum.h", "special_hermite_polynomial_he_ops.h", "hstack_native.h", "conv.h", "tensor.h", "glu_backward_jvp.h", "log.h", "where_native.h", "special_digamma.h", "repeat_interleave_native.h", "_foreach_acos_native.h", "any_module_holder.h", "metrics.h", "atanh_ops.h", "Sorting.h", "special_i0e_ops.h", "_to_dense_native.h", "ger.h", "_validate_sparse_bsr_tensor_args.h", "matrix_exp.h", "replication_pad3d_native.h", "special_legendre_polynomial_p_native.h", "acosh_meta.h", "special_erfinv.h", "_cudnn_rnn_backward_cuda_dispatch.h", "hstack.h", "flip_native.h", "_validate_sparse_bsc_tensor_args_native.h", "threshold_meta.h", "kl_div.h", "Float8_e5m2.h", "elu_backward.h", "ldexp_native.h", "linalg_lstsq.h", "_linalg_check_errors_native.h", "UpSampleKernelAVXAntialias.h", "_trilinear_ops.h", "broadcast_to_native.h", "dist_native.h", "sparse_sampled_addmm_native.h", "DistributionTemplates.h", "bilinear.h", "miopen_batch_norm_compositeexplicitautograd_dispatch.h", "native_batch_norm_native.h", "_embedding_bag_per_sample_weights_backward_native.h", "detach.h", "autocast_mode.h", "LegacyBatchedTensorImpl.h", "_test_warn_in_autograd.h", "SequenceNumber.h", "_upsample_nearest_exact3d_ops.h", "erfinv.h", "rnn.h", "tensor_flatten.h", "backend_interface.h", "sparse_coo_tensor_compositeimplicitautograd_dispatch.h", "_linalg_svd_meta.h", "CUDAGuard.h", "_embedding_bag_backward.h", "coalesce_ops.h", "min_ops.h", "_sobol_engine_ff_ops.h", "_sparse_coo_tensor_unsafe_ops.h", "ParamsHash.h", "native_group_norm.h", "_nnpack_available.h", "ConstexprCrc.h", "_unsafe_view_ops.h", "bitwise_or_native.h", "miopen_convolution_add_relu_native.h", "mkldnn_convolution_ops.h", "qembeddingbag.h", "aminmax_native.h", "PythonFallbackKernel.h", "_foreach_maximum.h", "special_modified_bessel_i1_meta.h", "rmsprop.h", "_fw_primal_copy_native.h", "round.h", "searchsorted_ops.h", "mish.h", "addmv_native.h", "_masked_softmax_ops.h", "to_padded_tensor.h", "fbgemm_pack_gemm_matrix_fp16_ops.h", "upsample_bicubic2d_cpu_dispatch.h", "Generator.h", "exponential_native.h", "value_selecting_reduction_backward.h", "serialize.h", "cauchy.h", "uniform_compositeexplicitautograd_dispatch.h", "bincount_native.h", "unique_consecutive_cuda_dispatch.h", "BatchingMetaprogramming.h", "optimizer.h", "_cdist_forward_ops.h", "function.h", "_sobol_engine_ff.h", "mean.h", "sspaddmm_ops.h", "_make_per_channel_quantized_tensor_native.h", "to_sparse_ops.h", "_sparse_bsr_tensor_unsafe_native.h", "logspace_ops.h", "qscheme_native.h", "expm1_native.h", "data_ops.h", "group_norm_ops.h", "_to_copy_compositeexplicitautograd_dispatch.h", "empty_permuted_native.h", "profiling_record.h", "fake_quantize_per_tensor_affine_native.h", "inliner.h", "upsample_nearest2d_cpu_dispatch.h", "lbfgs.h", "MPSAllocator.h", "upsample_bilinear2d_backward_cpu_dispatch.h", "half_support.h", "sort_meta.h", "_embedding_bag_dense_backward_native.h", "hardsigmoid_backward_ops.h", "mkldnn_rnn_layer.h", "logit_native.h", "upsample_nearest2d_backward.h", "fbgemm_pack_quantized_matrix_native.h", "cauchy_cuda_dispatch.h", "_empty_affine_quantized_ops.h", "gelu_native.h", "fft_irfftn.h", "nll_loss_backward_native.h", "_sparse_mm_reduce_impl_backward_native.h", "hardshrink_backward.h", "replication_pad1d_backward_native.h", "to_sparse_csc.h", "slice_backward_ops.h", "refine_names_native.h", "empty_permuted_compositeexplicitautograd_dispatch.h", "fix_native.h", "hinge_embedding_loss_native.h", "native_dropout.h", "fft_ihfft_native.h", "_slow_conv2d_forward_cpu_dispatch.h", "addbmm_ops.h", "lift_fresh_copy_native.h", "_coalesce_ops.h", "dsplit_native.h", "_upsample_bicubic2d_aa_backward_ops.h", "DeviceGuard.h", "_cslt_sparse_mm_native.h", "nuclear_norm_ops.h", "size.h", "_softmax_backward_data_meta.h", "rrelu_with_noise_ops.h", "nansum_cuda_dispatch.h", "sparse_coo_tensor_ops.h", "fft_irfft_native.h", "python_rpc_handler.h", "_nnpack_spatial_convolution_native.h", "hstack_ops.h", "_foreach_erfc_native.h", "take_along_dim_native.h", "native_layer_norm_backward_compositeexplicitautograd_dispatch.h", "_fused_adam_cuda_dispatch.h", "init.h", "greater_equal.h", "positive.h", "special_i1_ops.h", "upsample_nearest1d_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_nearest1d_backward.h", "_foreach_trunc.h", "_slow_conv2d_forward_ops.h", "adaptive_max_pool2d_backward_ops.h", "_foreach_cos_native.h", "cartesian_prod_ops.h", "_sobol_engine_scramble_native.h", "_fused_adamw_compositeexplicitautograd_dispatch.h", "pairwise_distance.h", "mkldnn_convolution.h", "_upsample_nearest_exact3d.h", "cumulative_trapezoid_native.h", "_sample_dirichlet_native.h", "logit_cuda_dispatch.h", "mse_loss.h", "Utils.h", "Dispatcher.h", "avg_pool3d_meta.h", "quantized_gru_cell_ops.h", "fft_ihfftn_compositeimplicitautograd_dispatch.h", "_upsample_nearest_exact1d_backward_ops.h", "cummin_native.h", "special_bessel_y0_ops.h", "UnaryOps.h", "segment_reduce_cpu_dispatch.h", "_linalg_svd_compositeexplicitautogradnonfunctional_dispatch.h", "pad_sequence_native.h", "stateless.h", "_unique_native.h", "max_pool2d_with_indices_backward_native.h", "fractional_max_pool2d.h", "_cufft_clear_plan_cache_ops.h", "bincount.h", "_nested_view_from_buffer_native.h", "_segment_reduce_backward_native.h", "slice_scatter.h", "_saturate_weight_to_fp16_native.h", "fbgemm_pack_gemm_matrix_fp16.h", "_thnn_fused_lstm_cell_compositeexplicitautograd_dispatch.h", "tensor.h", "linalg_cross.h", "lift_fresh_ops.h", "_conj_physical_native.h", "special_ndtri_native.h", "orgqr_native.h", "_foreach_addcmul_ops.h", "sparse_mask_native.h", "quantize_per_tensor_native.h", "_foreach_sinh.h", "sinh_native.h", "smooth_l1_loss_native.h", "backend.h", "bucketize.h", "nansum_ops.h", "upsample_bicubic2d_native.h", "tensor_dtypes.h", "max_ops.h", "Storage.h", "miopen_rnn_backward_cuda_dispatch.h", "argsort.h", "heaviside_meta.h", "poisson_nll_loss_ops.h", "hamming_window.h", "_reshape_alias_copy.h", "rrelu_with_noise_meta_dispatch.h", "argmax_native.h", "hardtanh_native.h", "_sample_dirichlet.h", "trace_backward_ops.h", "arctanh_native.h", "rnn_relu_cell_native.h", "chunk.h", "loopnest_randomization.h", "convolution_backward_ops.h", "_upsample_nearest_exact2d_backward.h", "special_chebyshev_polynomial_t_meta.h", "Sort.h", "max_unpool2d_ops.h", "retain_grad_native.h", "_cdist_backward_native.h", "batch_norm_gather_stats_with_counts_cuda_dispatch.h", "amin_native.h", "upsample_bilinear2d_backward_ops.h", "batch_norm_backward_reduce_native.h", "special_chebyshev_polynomial_v_native.h", "logaddexp_ops.h", "strtod.h", "special_sinc_ops.h", "layer_norm_ops.h", "native_layer_norm_compositeexplicitautograd_dispatch.h", "isinf_native.h", "_use_cudnn_ctc_loss_ops.h", "_fft_r2c_native.h", "logdet_ops.h", "fmax_ops.h", "bernoulli_compositeexplicitautograd_dispatch.h", "vec256_complex_float.h", "index_fill_ops.h", "atanh.h", "new_empty_ops.h", "PadNd.h", "cumprod_backward.h", "cudnn_is_acceptable_ops.h", "int_repr_ops.h", "sparse_bsc_tensor_ops.h", "special_bessel_y0.h", "_histogramdd_from_bin_cts_ops.h", "linalg_svd_native.h", "special_bessel_j0_native.h", "_thnn_fused_lstm_cell_backward_impl.h", "align_to_ops.h", "conv_depthwise3d_ops.h", "rad2deg_native.h", "_to_copy_native.h", "calculate_necessary_args.h", "select_copy_native.h", "special_exp2_native.h", "is_same_size_ops.h", "_upsample_bilinear2d_aa_backward.h", "_validate_sparse_csr_tensor_args.h", "fractional_max_pool3d_backward.h", "python_dict.h", "sparse_resize_ops.h", "python_strings.h", "shape_function_registry.h", "ccol_indices_copy_native.h", "dot.h", "custom_operator.h", "_histogramdd_from_bin_cts_cpu_dispatch.h", "fft_hfft2_ops.h", "_validate_sparse_bsr_tensor_args_ops.h", "_indices_ops.h", "_weight_norm_interface_backward.h", "_test_optional_floatlist_native.h", "hardtanh_backward.h", "_weight_norm_interface.h", "operator_name.h", "_cudnn_rnn_backward.h", "mse_loss_backward_ops.h", "_upsample_nearest_exact1d_compositeimplicitautograd_dispatch.h", "deg2rad_ops.h", "nll_loss2d_backward.h", "multi_wait.h", "coalesce.h", "special.h", "_conj_copy_ops.h", "set_ops.h", "t_ops.h", "masked_scatter_ops.h", "amax.h", "equal_ops.h", "upsample_nearest3d_backward_meta.h", "floor_divide_native.h", "gcd_meta.h", "randn_like.h", "clip_compositeimplicitautograd_dispatch.h", "convolution_backward_cuda_dispatch.h", "atleast_2d.h", "nansum.h", "_test_optional_filled_intlist.h", "fft_rfft2_compositeimplicitautograd_dispatch.h", "ones_like_compositeexplicitautograd_dispatch.h", "_slow_conv2d_backward.h", "_cast_Short.h", "_transform_bias_rescale_qkv_ops.h", "_upsample_nearest_exact1d_backward_meta.h", "true_divide_ops.h", "lowerings.h", "_foreach_tan_native.h", "native_batch_norm_cpu_dispatch.h", "softplus_backward.h", "_scaled_dot_product_flash_attention_native.h", "_gather_sparse_backward.h", "bernoulli_ops.h", "cumprod.h", "mkldnn_reorder_conv2d_weight_native.h", "_scaled_dot_product_efficient_attention.h", "sparse_csr_tensor_native.h", "_sparse_sum.h", "python_variable_indexing.h", "quantize_per_tensor.h", "special_erf_ops.h", "row_indices_ops.h", "cummaxmin_backward_native.h", "_dimV_native.h", "tree.h", "linalg_eigh.h", "lift.h", "cumsum_meta.h", "irange.h", "_linalg_svd_meta_dispatch.h", "upsample_bilinear2d_cpu_dispatch.h", "xor.h", "view_as_ops.h", "row_indices_copy_native.h", "pad_native.h", "rot90.h", "scatter_add_meta.h", "kthvalue_ops.h", "class_type.h", "recvrpc_backward.h", "empty_quantized_compositeexplicitautograd_dispatch.h", "quantile.h", "upsample_nearest1d_backward_cuda_dispatch.h", "cudnn_batch_norm_backward_ops.h", "Storage.h", "embedding_backward_ops.h", "batch_norm_gather_stats_with_counts.h", "squeeze_copy_ops.h", "atan_meta.h", "script_remote_call.h", "_neg_view_ops.h", "hypot_ops.h", "numpy_T_ops.h", "functional.h", "relu6_native.h", "native_dropout_compositeexplicitautograd_dispatch.h", "kineto_shim.h", "Unroll.h", "or_ops.h", "full_like_ops.h", "_euclidean_dist_ops.h", "nested_to_padded_tensor_compositeimplicitautograd_dispatch.h", "_fake_quantize_learnable_per_tensor_affine_native.h", "_is_zerotensor_ops.h", "subgraph_matcher.h", "_unpack_dual.h", "_triton_multi_head_attention_ops.h", "mkldnn_linear_backward_weights.h", "_cudnn_rnn_flatten_weight_native.h", "multi_margin_loss_backward_cuda_dispatch.h", "std_cpu_dispatch.h", "reflection_pad1d_native.h", "multilabel_margin_loss_backward.h", "_fake_quantize_learnable_per_tensor_affine_ops.h", "cumprod_cpu_dispatch.h", "rrelu_with_noise_backward.h", "linear_compositeexplicitautograd_dispatch.h", "real.h", "arccos_ops.h", "miopen_convolution.h", "select_backward_ops.h", "aminmax_compositeexplicitautogradnonfunctional_dispatch.h", "fbgemm_linear_fp16_weight_fp32_activation_native.h", "shared.h", "frozen_conv_folding.h", "native_layer_norm.h", "col2im_ops.h", "_nested_view_from_buffer_copy_ops.h", "_histogramdd_bin_edges_ops.h", "frobenius_norm_native.h", "_convolution_double_backward.h", "mish_backward_native.h", "asin_ops.h", "upsample_bilinear2d.h", "_sparse_coo_tensor_with_dims_and_tensors_meta_dispatch.h", "_upsample_nearest_exact3d_backward.h", "divide_ops.h", "addcmul_meta.h", "value_selecting_reduction_backward_native.h", "gather_backward_native.h", "EmbeddingBag.h", "polygamma_ops.h", "sinc_ops.h", "special_xlog1py_meta.h", "special_multigammaln_ops.h", "cummin.h", "_sparse_sparse_matmul.h", "logit_cpu_dispatch.h", "combinations_native.h", "frozen_conv_add_relu_fusion.h", "sum_to_size_ops.h", "pad_sequence_ops.h", "aminmax_cpu_dispatch.h", "hann_window_native.h", "smooth_l1_loss.h", "_add_relu_ops.h", "export_bytecode.h", "sym_stride_native.h", "detach_ops.h", "rrelu_ops.h", "instruction.h", "_to_dense_ops.h", "Function.h", "collate.h", "binary_cross_entropy_cuda_dispatch.h", "jit_utils.h", "bmm.h", "fixup_trace_scope_blocks.h", "debug_info.h", "_thnn_fused_lstm_cell_backward_impl_native.h", "linalg_norm.h", "_mkldnn_transpose_ops.h", "new_zeros.h", "special_sinc_native.h", "channel_shuffle_native.h", "rand_like_ops.h", "fft_ifft_native.h", "cloneable.h", "to_mkldnn_compositeexplicitautograd_dispatch.h", "fbgemm_linear_quantize_weight_native.h", "HIPGuardImplMasqueradingAsCUDA.h", "enum.h", "is_nonzero.h", "align_to.h", "worker_exception.h", "sin_native.h", "lt_meta.h", "fractional_max_pool3d_meta.h", "forward_grad.h", "slice_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_backward.h", "types.h", "lu_solve_native.h", "fractional_max_pool3d_ops.h", "_cudnn_rnn_backward_ops.h", "nll_loss2d_backward_cuda_dispatch.h", "distributed.h", "lstm_cell_ops.h", "_spdiags_native.h", "special_modified_bessel_i0_ops.h", "nll_loss.h", "CUDASparseDescriptors.h", "linalg_tensorsolve.h", "to_sparse_native.h", "helper.h", "diag_ops.h", "slice_copy.h", "gather.h", "isin_meta.h", "gru_ops.h", "nonzero_numpy.h", "less_native.h", "maximum_ops.h", "poisson_ops.h", "erfinv_meta.h", "logdet_native.h", "_conj_copy_native.h", "multinomial_cuda_dispatch.h", "cache.h", "sym_constrain_range_for_size_native.h", "ReduceAllOps.h", "unbind_copy_ops.h", "arctan2.h", "resize_as_sparse.h", "log_normal_native.h", "pow.h", "_scaled_dot_product_attention_math.h", "_nested_tensor_storage_offsets.h", "Interpreter.h", "MapAllocator.h", "tensor_impl.h", "expand_copy_ops.h", "histc_native.h", "StringUtil.h", "quantize_per_channel.h", "cudnn-wrapper.h", "_sample_dirichlet_compositeexplicitautograd_dispatch.h", "matmul.h", "t_native.h", "resize_as_ops.h", "native_norm_compositeexplicitautograd_dispatch.h", "uniform_meta_dispatch.h", "_efficient_attention_backward_native.h", "_nested_tensor_from_tensor_list_compositeexplicitautograd_dispatch.h", "adaptive_max_pool2d_backward_native.h", "mkldnn_rnn_layer_backward_native.h", "vml.h", "dropout_ops.h", "_upsample_nearest_exact1d_meta.h", "batch_norm_update_stats_native.h", "cummaxmin_backward.h", "linalg_svdvals_compositeimplicitautograd_dispatch.h", "_amp_foreach_non_finite_check_and_unscale_ops.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_native.h", "frobenius_norm.h", "to_mkldnn_backward_native.h", "to_sparse_csr_compositeimplicitautograd_dispatch.h", "index.h", "histogramdd_compositeimplicitautograd_dispatch.h", "fft_fftfreq_compositeexplicitautograd_dispatch.h", "xnnpack.h", "rrelu_with_noise_backward_native.h", "conv_transpose2d_compositeimplicitautograd_dispatch.h", "uniform_cpu_dispatch.h", "special_xlogy.h", "median_ops.h", "unpickled_python_remote_call.h", "_upsample_nearest_exact3d_backward_meta.h", "topk.h", "vdot.h", "_to_sparse_semi_structured_native.h", "set_data_ops.h", "ltc_ops.h", "contiguous.h", "_adaptive_avg_pool3d_ops.h", "_to_cpu_native.h", "special_hermite_polynomial_h_meta.h", "CuFFTPlanCache.h", "to_sparse_bsr_compositeimplicitautograd_dispatch.h", "lstm_mps_backward.h", "_upsample_nearest_exact1d_cuda_dispatch.h", "cholesky.h", "trunc.h", "empty_strided_meta_dispatch.h", "special_log_ndtr.h", "logical_or_native.h", "reshape_native.h", "_make_dual_native.h", "count_nonzero_ops.h", "margin_ranking_loss_native.h", "_to_sparse_ops.h", "kl_div_native.h", "multilabel_margin_loss_backward_native.h", "_foreach_minimum_ops.h", "i0_ops.h", "silu.h", "frozen_concat_linear.h", "to_sparse_csc_compositeimplicitautograd_dispatch.h", "rrelu_with_noise_cuda_dispatch.h", "unsafe_split.h", "rsqrt_ops.h", "special_zeta_native.h", "nonzero_native.h", "affine_grid_generator_backward_native.h", "grid_sampler_3d.h", "adaptive_max_pool3d.h", "_foreach_copy.h", "sugared_value.h", "import_export_common.h", "_sparse_semi_structured_linear_cuda_dispatch.h", "mul_native.h", "_nested_tensor_storage_offsets_native.h", "DeviceGuard.h", "imag_native.h", "angle_ops.h", "PointwiseOps.h", "quantized_max_pool3d_ops.h", "fft_rfft_ops.h", "upsample_nearest3d_native.h", "fft_irfftn_compositeimplicitautograd_dispatch.h", "GeneratorForPrivateuseone.h", "positive_ops.h", "conv_transpose2d.h", "expand_as_native.h", "UnfoldBackward.h", "tensor_split.h", "concat_native.h", "to_mkldnn_native.h", "any.h", "to_sparse_bsr_ops.h", "special_modified_bessel_i1.h", "align_as_native.h", "_foreach_round_native.h", "CUDAContext.h", "stmt.h", "Size.h", "col_indices_ops.h", "all.h", "norm_except_dim.h", "diff.h", "atanh_meta.h", "equal.h", "_masked_softmax_backward_cpu_dispatch.h", "upsample_bicubic2d_backward_ops.h", "function_impl.h", "special_bessel_j1_native.h", "index_select_backward_native.h", "_resize_output.h", "bilinear_native.h", "index_reduce.h", "_cast_Char_native.h", "python_custom_class.h", "blackman_window.h", "complex_math.h", "miopen_rnn.h", "_sparse_bsc_tensor_unsafe_native.h", "variable_tensor_list.h", "binary_cross_entropy_with_logits_native.h", "cudnn_grid_sampler_backward.h", "count_nonzero_native.h", "inverse_ops.h", "_sparse_sparse_matmul_native.h", "_linalg_eigh_meta.h", "_foreach_maximum_native.h", "exit_transforms.h", "mean_cpu_dispatch.h", "swapaxes.h", "special_entr.h", "adaptive_max_pool3d_backward_native.h", "nextafter_meta.h", "quantized_rnn_relu_cell.h", "_sparse_semi_structured_linear_native.h", "_test_autograd_multiple_dispatch.h", "max_pool2d_ops.h", "ones.h", "tanh_backward.h", "ir_emitter.h", "special_bessel_j1_ops.h", "max_pool1d_native.h", "List_inl.h", "_debug_has_internal_overlap_native.h", "_embedding_bag_dense_backward_cuda_dispatch.h", "upsample_trilinear3d_backward_ops.h", "poisson_cuda_dispatch.h", "atleast_1d.h", "RangeFactories.h", "constant_pooling.h", "outer.h", "permute.h", "index_select.h", "linalg_multi_dot_ops.h", "_convolution_double_backward_native.h", "special_shifted_chebyshev_polynomial_t.h", "python_numbers.h", "backend_preprocess.h", "_upsample_nearest_exact2d_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_qr_meta.h", "conv3d.h", "gather_meta.h", "poisson_nll_loss_native.h", "_fw_primal_copy.h", "_propagate_xla_data.h", "_histogramdd_from_bin_tensors_native.h", "thread_constants.h", "logcumsumexp.h", "std_mean.h", "max_unpool2d.h", "_grid_sampler_2d_cpu_fallback_backward_ops.h", "InlineDeviceGuard.h", "softplus_ops.h", "matmul_ops.h", "_foreach_clamp_max_native.h", "_to_sparse_csr_compositeexplicitautograd_dispatch.h", "hypot_native.h", "flatbuffer_serializer.h", "can_cast.h", "graph_executor.h", "special_digamma_native.h", "_adaptive_avg_pool2d_ops.h", "quantized_lstm_cell_ops.h", "cudnn_convolution_add_relu.h", "TensorMeta.h", "_upsample_nearest_exact3d_cuda_dispatch.h", "pairwise_distance_ops.h", "_coalesce.h", "_validate_sparse_coo_tensor_args_ops.h", "_validate_sparse_coo_tensor_args_compositeimplicitautograd_dispatch.h", "_values_ops.h", "rnn_relu_ops.h", "l1_loss.h", "frexp_native.h", "mkldnn_max_pool2d_backward_native.h", "put_ops.h", "Half.h", "eq_ops.h", "cdist_compositeimplicitautograd_dispatch.h", "_thnn_fused_lstm_cell_native.h", "lambda.h", "_upsample_nearest_exact2d_backward_cpu_dispatch.h", "python_cpp_function.h", "linalg_eigh_native.h", "_mkldnn_reshape.h", "transpose_ops.h", "fft_ifft2_ops.h", "upsample_trilinear3d_backward_meta.h", "scaled_dot_product_attention_native.h", "_cslt_compress_native.h", "tracer.h", "embedding_bag_ops.h", "_weight_norm_native.h", "batch_norm_compositeimplicitautograd_dispatch.h", "embedding_sparse_backward_native.h", "linalg_eigh_ops.h", "transpose_copy.h", "convolution_backward_native.h", "_to_sparse_csc.h", "lgamma.h", "_to_sparse_csc_cpu_dispatch.h", "lshift_ops.h", "_pdist_backward_native.h", "histogram_ops.h", "tril_ops.h", "_sparse_mm_native.h", "qscheme.h", "rnn_relu_cell_ops.h", "smooth_l1_loss_backward_ops.h", "special_hermite_polynomial_h_ops.h", "fractional_max_pool3d_native.h", "UniqueVoidPtr.h", "_fft_r2c_ops.h", "embedding_sparse_backward.h", "quantized_lstm_cell.h", "cosine_embedding_loss_ops.h", "init.h", "_pad_circular.h", "kthvalue_native.h", "linalg_inv_ex_native.h", "native_group_norm_cuda_dispatch.h", "_foreach_erf_ops.h", "acosh_native.h", "adamw.h", "_standard_gamma.h", "igammac.h", "empty_permuted_ops.h", "_embedding_bag_dense_backward.h", "fake_quantize_per_tensor_affine.h", "_empty_per_channel_affine_quantized_native.h", "output_nr_ops.h", "special_log_ndtr_ops.h", "_grid_sampler_2d_cpu_fallback_native.h", "linear_backward.h", "tensor_list.h", "_foreach_zero.h", "addmv.h", "hann_window.h", "OptionalArrayRef.h", "inner_native.h", "clone_compositeexplicitautograd_dispatch.h", "slogdet.h", "trapz_native.h", "special_scaled_modified_bessel_k0_native.h", "vulkan.h", "mkldnn_convolution_compositeexplicitautograd_dispatch.h", "_foreach_sinh_ops.h", "tensor_apply.h", "selu_native.h", "multilabel_margin_loss_forward_native.h", "lambda_post_hook.h", "unflatten_native.h", "Normalization.h", "Loops.h", "special_erfcx_meta.h", "_transformer_encoder_layer_fwd_compositeexplicitautograd_dispatch.h", "div.h", "utils.h", "upsample_linear1d_backward_meta.h", "fill_ops.h", "fft_fftn_ops.h", "tile.h", "exponential_ops.h", "_cdist_forward_compositeexplicitautograd_dispatch.h", "bitwise_right_shift_ops.h", "new_empty_compositeexplicitautograd_dispatch.h", "_sobol_engine_draw_native.h", "_foreach_ceil_ops.h", "upsample_nearest1d_cuda_dispatch.h", "normal_meta_dispatch.h", "pow_ops.h", "max_pool1d_with_indices_ops.h", "_functional_sym_constrain_range_ops.h", "linalg_lu_factor_native.h", "ir_cloner.h", "mode_ops.h", "silu_backward_native.h", "to_sparse_compositeimplicitautograd_dispatch.h", "geometric_native.h", "_upsample_bilinear2d_aa_compositeimplicitautograd_dispatch.h", "glu_meta.h", "cross.h", "requires_grad_analysis.h", "bmm_meta.h", "_indices.h", "scatter_reduce_meta.h", "fbgemm_linear_int8_weight_native.h", "igammac_ops.h", "_to_sparse_bsc_cpu_dispatch.h", "nanmedian_native.h", "avg_pool3d_cuda_dispatch.h", "pin_memory_native.h", "_unsafe_index_ops.h", "sym_constrain_range_compositeexplicitautograd_dispatch.h", "upsample_bilinear2d_ops.h", "_thnn_fused_lstm_cell_cuda_dispatch.h", "cpp_stacktraces.h", "hann_window_ops.h", "aten_interned_strings.h", "crow_indices_ops.h", "propagate_gradients_resp.h", "nan_to_num_cpu_dispatch.h", "upsample_nearest3d_compositeimplicitautograd_dispatch.h", "linalg_cholesky_ex_ops.h", "result_type_native.h", "fft_fft2_native.h", "linalg_vector_norm_cuda_dispatch.h", "upsample_bilinear2d_cuda_dispatch.h", "fmax_native.h", "multiply.h", "convolution_backward_compositeexplicitautograd_dispatch.h", "conv_tbc_backward_native.h", "mkldnn_linear.h", "autodiff.h", "linalg_slogdet.h", "linalg_vander_compositeimplicitautograd_dispatch.h", "_foreach_norm.h", "multi_margin_loss_backward_cpu_dispatch.h", "_test_optional_intlist_ops.h", "import_data.h", "linalg_cond_ops.h", "istft_native.h", "_embedding_bag_compositeexplicitautograd_dispatch.h", "quantized_max_pool1d_ops.h", "outer_native.h", "_cast_Double_ops.h", "flat_hash_map.h", "flatten_ops.h", "gt_native.h", "special_shifted_chebyshev_polynomial_v.h", "isposinf_meta.h", "MPSStream.h", "soft_margin_loss_backward.h", "rand_like_compositeexplicitautograd_dispatch.h", "_linalg_slogdet_ops.h", "slow_conv_transpose2d_native.h", "ParamUtils.h", "output_nr_native.h", "grid_sampler.h", "hardsigmoid_backward_native.h", "typeid.h", "unique_consecutive_native.h", "_thnn_fused_gru_cell_native.h", "feature_alpha_dropout_ops.h", "binomial_ops.h", "_validate_sparse_compressed_tensor_args_ops.h", "reflection_pad3d_backward_ops.h", "mse_loss_meta.h", "linalg_eigvalsh.h", "_sobol_engine_draw_compositeimplicitautograd_dispatch.h", "Padding.h", "internals.h", "pointwise.h", "masked_scatter.h", "vsplit_ops.h", "isneginf_native.h", "special_chebyshev_polynomial_w_ops.h", "vstack_native.h", "normalization.h", "convolution_backward.h", "adaptive_avg_pool2d.h", "special_polygamma_ops.h", "batch_norm_gather_stats_with_counts_native.h", "symbol.h", "istft_ops.h", "xlogy.h", "masked_fill_ops.h", "_unique2_native.h", "eq_meta.h", "_sparse_bsr_tensor_unsafe.h", "float_power_native.h", "infinitely_differentiable_gelu_backward.h", "miopen_batch_norm_backward_compositeexplicitautograd_dispatch.h", "is_neg_ops.h", "mkldnn_linear_backward_input_native.h", "erase_number_types.h", "asinh_meta.h", "_native_multi_head_attention_cuda_dispatch.h", "normal_ops.h", "_spdiags_compositeexplicitautograd_dispatch.h", "bitwise_and_meta.h", "max_pool1d.h", "IdWrapper.h", "_fake_quantize_learnable_per_channel_affine_backward_ops.h", "max_pool2d_with_indices_backward_meta.h", "special_logit_ops.h", "canonicalize_modified_loop.h", "QScheme.h", "shape_analysis.h", "_propagate_xla_data_native.h", "cauchy_compositeexplicitautograd_dispatch.h", "_thnn_differentiable_lstm_cell_backward_compositeimplicitautograd_dispatch.h", "inner_ops.h", "column_stack.h", "_sparse_coo_tensor_with_dims_and_tensors.h", "grid_sampler_2d_native.h", "_native_batch_norm_legit_ops.h", "ir.h", "pdist_native.h", "special_round.h", "Dict_inl.h", "_linalg_svd_cuda_dispatch.h", "callstack_debug_info_serialization.h", "CUDAException.h", "infinitely_differentiable_gelu_backward_native.h", "special_ndtr.h", "_upsample_nearest_exact2d_backward_ops.h", "canonicalize.h", "logical_and_native.h", "_upsample_bilinear2d_aa_ops.h", "is_distributed_native.h", "index_reduce_ops.h", "logit_backward.h", "_nested_select_backward_native.h", "nonzero_static_native.h", "clamp_max_meta.h", "TensorNames.h", "IListRef_inl.h", "tensor_util.h", "_cast_Short_ops.h", "CUDADeviceAssertionHost.h", "new_zeros_native.h", "AccumulateType.h", "_resize_output_ops.h", "split_with_sizes_copy_native.h", "_efficient_attention_backward_ops.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_ops.h", "_triton_scaled_dot_attention_ops.h", "flatten_native.h", "linalg_cholesky_ops.h", "atan.h", "sigmoid_backward_ops.h", "_nested_tensor_from_mask_left_aligned.h", "prod_meta_dispatch.h", "TypeDefault.h", "div_compositeexplicitautograd_dispatch.h", "python_util.h", "upsample_bilinear2d_meta.h", "_remove_batch_dim_ops.h", "special_sinc.h", "fft_rfft_native.h", "batch_norm_backward_reduce.h", "CPUFallback.h", "cdist_native.h", "softshrink_backward_meta.h", "llvm_codegen.h", "miopen_depthwise_convolution_compositeexplicitautograd_dispatch.h", "constant_pad_nd_ops.h", "special_scaled_modified_bessel_k0_meta.h", "huber_loss_ops.h", "linalg_ldl_solve.h", "upsample_nearest2d_native.h", "alias.h", "special_chebyshev_polynomial_u_meta.h", "_sparse_mm_reduce_impl_ops.h", "rshift_ops.h", "linalg_lu_solve_ops.h", "count_nonzero.h", "error.h", "quantile_native.h", "onednn_graph_fuser.h", "logdet.h", "argmax_meta_dispatch.h", "ScopeExit.h", "sum_cpu_dispatch.h", "pixel_shuffle.h", "_cufft_set_plan_cache_max_size_native.h", "col2im.h", "fft_rfftfreq_compositeexplicitautograd_dispatch.h", "misc.h", "OpaqueTensorImpl.h", "named_value.h", "true_divide.h", "_grid_sampler_2d_cpu_fallback.h", "gelu_backward_ops.h", "_validate_sparse_bsc_tensor_args_ops.h", "binary_cross_entropy_backward_cpu_dispatch.h", "fold_linear_bn.h", "Registry.h", "rad2deg_ops.h", "_gather_sparse_backward_ops.h", "fft_irfft2_ops.h", "update_graph_executor_opt.h", "_scaled_dot_product_efficient_attention_cuda_dispatch.h", "selu.h", "nanmean.h", "_dimI.h", "q_per_channel_scales_ops.h", "special_xlog1py_ops.h", "python_function.h", "special_ndtri_ops.h", "tanh_backward_native.h", "string_view.h", "gather_ops.h", "adaptive_max_pool2d_meta.h", "new_full_compositeexplicitautograd_dispatch.h", "linalg_solve_ops.h", "_reshape_copy_native.h", "view_as_real_ops.h", "_pack_padded_sequence_backward.h", "_amp_update_scale_native.h", "nextafter.h", "TypeList.h", "special_shifted_chebyshev_polynomial_u_meta.h", "concat_ops.h", "norm_ops.h", "linalg_vander_native.h", "blackman_window_native.h", "upsample_nearest3d_backward_native.h", "transformerlayer.h", "from_file_cpu_dispatch.h", "nanmean_native.h", "from_blob.h", "inline_fork_wait.h", "graph_executor_impl.h", "celu_native.h", "adaptive_avg_pool1d.h", "_validate_sparse_bsr_tensor_args_native.h", "upsample_bilinear2d_compositeimplicitautograd_dispatch.h", "_sparse_broadcast_to_copy.h", "_sparse_csr_tensor_unsafe.h", "index_select_backward_ops.h", "istft.h", "row_stack_native.h", "TensorAdvancedIndexingUtils.h", "update_differentiable_graph_requires_grad.h", "conv_transpose2d_ops.h", "tanh_ops.h", "linalg_qr_ops.h", "_foreach_addcmul.h", "bit_cast.h", "lgamma_native.h", "ConstantSymNodeImpl.h", "_efficient_attention_backward_cuda_dispatch.h", "_convolution_mode.h", "huber_loss_backward_ops.h", "_assert_tensor_metadata.h", "_fused_moving_avg_obs_fq_helper_ops.h", "variable_factories.h", "miopen_batch_norm_backward_ops.h", "log10.h", "reflection_pad2d.h", "_cufft_clear_plan_cache_native.h", "unflatten_dense_tensors_ops.h", "cos_ops.h", "upsample_nearest1d_backward_ops.h", "upsample_trilinear3d_backward_cuda_dispatch.h", "ne_meta.h", "range.h", "utils.h", "upsample_nearest2d_meta.h", "file_format.h", "view_as_real_native.h", "matmul_backward.h", "Dict.h", "unbind_ops.h", "sparse_resize_native.h", "thnn_conv2d_native.h", "inverse.h", "_cdist_backward.h", "NonSymbolicBC.h", "prelu.h", "python_special_functions.h", "full_like_native.h", "binary_cross_entropy_backward_ops.h", "conv1d_ops.h", "broadcast_tensors_ops.h", "special_hermite_polynomial_he_meta.h", "bitwise_left_shift_ops.h", "_to_sparse.h", "_nested_from_padded_and_nested_example_native.h", "special_airy_ai_meta.h", "_foreach_reciprocal_ops.h", "to_sparse.h", "upsample_nearest2d_cuda_dispatch.h", "divide_compositeimplicitautograd_dispatch.h", "is_pinned_ops.h", "DynamicTypes.h", "atan2_native.h", "amax_native.h", "_nested_tensor_storage_offsets_ops.h", "_thnn_fused_lstm_cell_backward.h", "_fused_sdp_choice.h", "tanh_backward_ops.h", "_to_copy_ops.h", "Metaprogramming.h", "scatter_add_ops.h", "tanh_meta.h", "mps_convolution_transpose_backward.h", "q_per_channel_zero_points_ops.h", "upsample_trilinear3d_backward_native.h", "upsample_nearest3d_compositeexplicitautogradnonfunctional_dispatch.h", "stack.h", "special_entr_native.h", "peephole.h", "_reshape_alias_copy_ops.h", "versioned_symbols.h", "to_padded_tensor_native.h", "_triton_scaled_dot_attention.h", "native_batch_norm_backward_native.h", "PythonOpRegistrationTrampoline.h", "avg_pool2d_backward_native.h", "special_modified_bessel_i0.h", "Backend.h", "ge.h", "nested_to_padded_tensor_ops.h", "fft_rfftfreq_ops.h", "fbgemm_linear_fp16_weight_ops.h", "special_bessel_j0_meta.h", "cudnn_grid_sampler_backward_native.h", "utils.h", "is_floating_point_ops.h", "sign.h", "grid_sampler_native.h", "sum_native.h", "_upsample_bicubic2d_aa_ops.h", "_backward_ops.h", "ctc_loss_ops.h", "_upsample_nearest_exact3d_backward_cuda_dispatch.h", "intrusive_ptr.h", "fft_ihfft_compositeimplicitautograd_dispatch.h", "var.h", "BinaryInternal.h", "channel_shuffle_ops.h", "_to_sparse_bsr_native.h", "_validate_sparse_csr_tensor_args_native.h", "slow_conv3d_forward_cpu_dispatch.h", "ir_builder.h", "custom_class.h", "specialize_autogradzero.h", "nuclear_norm_native.h", "_thnn_fused_lstm_cell_backward_impl_cuda_dispatch.h", "upsample_linear1d_cpu_dispatch.h", "NamedTensorUtils.h", "_sparse_softmax_compositeimplicitautograd_dispatch.h", "hardshrink.h", "_make_dual_copy.h", "mkldnn_convolution_native.h", "reflection_pad3d_backward.h", "narrow_copy.h", "_scaled_dot_product_efficient_attention_backward_cuda_dispatch.h", "eye_ops.h", "nll_loss_backward_meta.h", "TensorIndexing.h", "embedding_dense_backward.h", "fbgemm_linear_int8_weight_fp32_activation_native.h", "linalg_tensorsolve_compositeimplicitautograd_dispatch.h", "arcsin_native.h", "_upsample_nearest_exact2d_meta_dispatch.h", "max_pool2d_with_indices.h", "_scaled_dot_product_flash_attention.h", "_embedding_bag_forward_only_compositeexplicitautograd_dispatch.h", "batchnorm.h", "nested.h", "_logcumsumexp.h", "register_packed_params.h", "_cast_Byte.h", "linalg_solve_ex_ops.h", "fft_ifft_compositeimplicitautograd_dispatch.h", "GridSampler.h", "special_hermite_polynomial_he.h", "vstack_ops.h", "_linalg_det.h", "convolution_overrideable_compositeexplicitautograd_dispatch.h", "storage_context.h", "fractional_max_pool3d_backward_ops.h", "var_compositeimplicitautograd_dispatch.h", "multi_margin_loss.h", "thnn_conv2d_ops.h", "alpha_dropout_ops.h", "logical_and.h", "q_zero_point.h", "miopen_rnn_cuda_dispatch.h", "hardswish_backward.h", "index_put_native.h", "chain_matmul.h", "refine_names.h", "_values.h", "less_ops.h", "DefaultTensorOptions.h", "reflection_pad1d_backward_native.h", "multi_margin_loss_backward.h", "narrow_ops.h", "_foreach_pow_native.h", "ordered_dict.h", "row_indices_copy_ops.h", "triplet_margin_loss.h", "fft_ihfftn_ops.h", "cos_native.h", "_test_optional_floatlist.h", "in_memory_adapter.h", "signbit_meta.h", "fractional_max_pool2d_backward_native.h", "special_chebyshev_polynomial_w_native.h", "nll_loss_nd_native.h", "FunctionsManual.h", "_index_put_impl_meta_dispatch.h", "_test_warn_in_autograd_native.h", "cudnn_grid_sampler_native.h", "cudnn_batch_norm_ops.h", "_embedding_bag_forward_only_cpu_dispatch.h", "_nested_tensor_from_mask_ops.h", "new_empty_strided.h", "bitwise_left_shift.h", "rand_ops.h", "_foreach_sigmoid_native.h", "request_callback_no_python.h", "_functional_assert_async_ops.h", "_sparse_softmax_ops.h", "view_copy_native.h", "_linalg_slogdet_native.h", "_upsample_nearest_exact2d_backward_cuda_dispatch.h", "argwhere_native.h", "cartesian_prod_native.h", "special_shifted_chebyshev_polynomial_v_native.h", "leaky_relu_backward.h", "multi_margin_loss_ops.h", "special_i1e_ops.h", "cross_entropy_loss_ops.h", "concatenate_native.h", "xlogy_native.h", "searchsorted_cuda_dispatch.h", "conv_transpose3d.h", "fft_hfft_ops.h", "ge_ops.h", "special_logit_native.h", "_functional_sym_constrain_range_native.h", "_convolution_mode_ops.h", "_sparse_softmax_backward_data_native.h", "transpose.h", "retains_grad_ops.h", "special_psi_native.h", "detach_copy_ops.h", "ivalue_inl.h", "_cast_Half_ops.h", "cholesky_inverse_native.h", "_sparse_sum_backward_ops.h", "_mkldnn_transpose_native.h", "_nested_sum_backward.h", "value_refinement_utils.h", "function.h", "batch_norm.h", "_upsample_bilinear2d_aa.h", "lift_fresh.h", "det_native.h", "_upsample_bicubic2d_aa_meta_dispatch.h", "affine_grid_generator_backward_ops.h", "_histogramdd_bin_edges.h", "zeros_like_compositeexplicitautograd_dispatch.h", "vec256_bfloat16.h", "bernoulli_cuda_dispatch.h", "rref_backward_req.h", "_foreach_div_native.h", "norm.h", "output_nr.h", "lgamma_meta.h", "view_as_complex_copy.h", "cudnn_affine_grid_generator_native.h", "_sobol_engine_scramble_ops.h", "OnednnUtils.h", "KernelFunction_impl.h", "_linalg_eigh_ops.h", "lerp_ops.h", "fft_irfft2.h", "trapezoid.h", "serialized_shape_function_registry.h", "_logcumsumexp_ops.h", "unsqueeze_copy.h", "quantized_max_pool3d.h", "clamp_cpu_dispatch.h", "_to_sparse_csr_native.h", "unsafe_split_with_sizes.h", "dist.h", "arange_ops.h", "distance.h", "_native_batch_norm_legit_native.h", "floating_point_utils.h", "sinh_meta.h", "fake_quantize_per_channel_affine_native.h", "resolve_neg_native.h", "avg_pool1d_native.h", "multi_margin_loss_backward_native.h", "_mps_convolution_transpose_native.h", "roll.h", "loopnest.h", "promote_types_native.h", "uniform_native.h", "resolve_neg_ops.h", "_new_zeros_with_same_feature_meta_ops.h", "convert_parameters.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams.h", "cumprod_ops.h", "binary_cross_entropy_with_logits_ops.h", "_nnpack_spatial_convolution_compositeexplicitautograd_dispatch.h", "glu_backward_jvp_native.h", "profiler_python.h", "uniform_cuda_dispatch.h", "index_fill_native.h", "_foreach_reciprocal.h", "padding.h", "to_sparse_csc_ops.h", "empty_strided_native.h", "rand_like.h", "DistributionTemplates.h", "_to_sparse_bsc_cuda_dispatch.h", "softmax.h", "norm_except_dim_native.h", "_nnz.h", "isnan.h", "native_dropout_backward_native.h", "atleast_2d_native.h", "cdist.h", "DeviceArray.h", "replication_pad3d_backward_native.h", "lstm_mps_backward_ops.h", "_fake_quantize_learnable_per_tensor_affine_backward_ops.h", "fft_irfftn_ops.h", "softmax_ops.h", "sparse_csc_tensor_ops.h", "retains_grad.h", "python_anomaly_mode.h", "onnx.h", "avg_pool3d.h", "script_init.h", "softplus_backward_meta.h", "fake_quantize_per_tensor_affine_cachemask.h", "QuantizedOps.h", "log_sigmoid_backward.h", "conv2d.h", "_foreach_sin_ops.h", "_cudnn_rnn_backward_compositeexplicitautograd_dispatch.h", "symbolic_shape_cache.h", "_weight_norm_differentiable_backward.h", "thread_pool.h", "_copy_from_and_resize_ops.h", "quantized_max_pool2d_ops.h", "dropout.h", "gru_cell_ops.h", "mkldnn_linear_native.h", "msort.h", "unsqueeze_copy_native.h", "upsample_linear1d_backward_ops.h", "qembeddingbag_prepack.h", "linalg_lu_solve.h", "ctc_loss_native.h", "conj_physical_native.h", "Distributions.h", "to_dense_backward.h", "fold.h", "_index_put_impl_cpu_dispatch.h", "argwhere.h", "fft_rfftn_native.h", "slice_native.h", "logit_backward_cpu_dispatch.h", "pin_memory_compositeimplicitautograd_dispatch.h", "_empty_per_channel_affine_quantized_ops.h", "_foreach_frac_native.h", "matrix_power_ops.h", "clone_native.h", "_foreach_minimum_native.h", "softmax_compositeimplicitautograd_dispatch.h", "rnn_tanh_ops.h", "eye.h", "select_copy.h", "linalg_cond_compositeimplicitautograd_dispatch.h", "CachedTensorUtils.h", "fft_irfft2_native.h", "empty_quantized.h", "sparse_csr_tensor.h", "trace_ops.h", "adaptive_avg_pool3d_backward.h", "matmul_native.h", "acos.h", "cumsum_cuda_dispatch.h", "linalg_svdvals_native.h", "crow_indices_native.h", "replication_pad3d_ops.h", "conv_depthwise3d.h", "_nested_tensor_size_ops.h", "binomial_compositeexplicitautograd_dispatch.h", "index_put_compositeexplicitautograd_dispatch.h", "_sparse_mm_ops.h", "ThreadLocalDebugInfo.h", "int_repr.h", "_weight_norm_differentiable_backward_native.h", "_foreach_sqrt.h", "special_ndtri.h", "remainder_native.h", "_linalg_solve_ex_meta.h", "mkldnn_linear_backward_weights_ops.h", "isin.h", "type_as_ops.h", "softplus_backward_native.h", "LogAddExp.h", "fmax_meta.h", "sum_compositeimplicitautograd_dispatch.h", "_convolution_mode_compositeimplicitautograd_dispatch.h", "pythoncapi_compat.h", "linalg_svd.h", "special_chebyshev_polynomial_w_meta.h", "values_copy.h", "ones_compositeexplicitautograd_dispatch.h", "fft_ifft_ops.h", "_conv_depthwise2d_native.h", "script_type_parser.h", "slogdet_native.h", "_nested_sum_backward_ops.h", "transformercoder.h", "_copy_from_and_resize.h", "ir_views.h", "to_sparse_bsc.h", "_segment_reduce_backward_ops.h", "slow_conv3d.h", "native_layer_norm_backward_cpu_dispatch.h", "_weight_norm_interface_ops.h", "compilation_unit.h", "native_batch_norm_backward_ops.h", "rrelu_with_noise_cpu_dispatch.h", "vec512_complex_float.h", "unflatten_ops.h", "max_pool3d_ops.h", "upsample_nearest2d_backward_cuda_dispatch.h", "linalg_ldl_factor_ex_native.h", "atan_native.h", "new_full_native.h", "ScalarType.h", "_thnn_differentiable_gru_cell_backward_native.h", "CUDAMiscFunctions.h", "argmin_meta_dispatch.h", "gelu_backward_native.h", "fft_fft.h", "log_sigmoid_ops.h", "prod_cpu_dispatch.h", "broadcast_to_ops.h", "_cast_Byte_native.h", "_addmm_activation_meta.h", "matrix_exp_native.h", "diagonal_scatter.h", "_fused_sdp_choice_cpu_dispatch.h", "kl_div_ops.h", "moduledict.h", "tensor_memoryformats.h", "_upsample_nearest_exact3d_meta_dispatch.h", "cudnn_convolution_ops.h", "mkldnn_reorder_conv2d_weight_compositeexplicitautograd_dispatch.h", "frame.h", "align_tensors_ops.h", "special_laguerre_polynomial_l_native.h", "cov.h", "stl.h", "rsub_native.h", "special_i1_meta.h", "type_name_uniquer.h", "TensorGeometry.h", "one_hot.h", "_upsample_nearest_exact1d_ops.h", "special_log1p_native.h", "_masked_softmax_backward_native.h", "reflection_pad1d.h", "trace_backward.h", "mish_ops.h", "segment_reduce_cuda_dispatch.h", "norm.h", "slow_conv_transpose2d_meta_dispatch.h", "UpSample.h", "linalg_matrix_exp_ops.h", "fake_quantize_per_tensor_affine_cachemask_backward_native.h", "argmax_compositeexplicitautogradnonfunctional_dispatch.h", "BFloat16-math.h", "_add_batch_dim_ops.h", "clog.h", "_foreach_sin.h", "clone.h", "clamp_max.h", "unique_dim_consecutive.h", "vararg_functions.h", "_foreach_clamp_min.h", "miopen_batch_norm_backward_native.h", "mkldnn_linear_compositeexplicitautograd_dispatch.h", "elu.h", "cholesky_inverse_ops.h", "mkldnn_reorder_conv3d_weight_ops.h", "fmax.h", "arctan2_ops.h", "cudnn_convolution_relu_ops.h", "multilabel_margin_loss_backward_ops.h", "max_pool2d_backward.h", "sqrt.h", "jiterator_impl.h", "schema_type_parser.h", "unfold_backward_ops.h", "leaky_relu_backward_ops.h", "ccol_indices.h", "view_native.h", "MPSProfiler.h", "upsample_bicubic2d_backward.h", "maximum_meta.h", "slow_conv3d_forward.h", "python_arg_parser.h", "frobenius_norm_ops.h", "to_dense_backward_ops.h", "pooling.h", "max_pool1d_ops.h", "reflection_pad3d_backward_meta.h", "special_multigammaln_native.h", "bitwise_xor.h", "hardsigmoid_native.h", "col_indices.h", "_validate_sparse_compressed_tensor_args_native.h", "std_mean_cuda_dispatch.h", "_embedding_bag_ops.h", "_mps_convolution_transpose.h", "Descriptors.h", "_test_optional_floatlist_compositeexplicitautograd_dispatch.h", "_cudnn_init_dropout_state_native.h", "special_logsumexp.h", "as_strided.h", "contiguous_compositeimplicitautograd_dispatch.h", "_weight_norm_interface_backward_native.h", "upgrader_mobile.h", "peephole_non_tensor.h", "batch_norm_update_stats_cuda_dispatch.h", "cos.h", "op_registration.h", "_cslt_sparse_mm_cuda_dispatch.h", "upsample_bicubic2d_cuda_dispatch.h", "qr_ops.h", "logaddexp2_ops.h", "method.h", "complex.h", "is_pinned_compositeexplicitautograd_dispatch.h", "VariableType.h", "adjoint.h", "pad_compositeimplicitautograd_dispatch.h", "_compute_linear_combination_native.h", "conv3d_ops.h", "descr.h", "EmptyTensor.h", "bernoulli_cpu_dispatch.h", "_thnn_fused_gru_cell_compositeexplicitautograd_dispatch.h", "ge_native.h", "topk_meta.h", "anomaly_mode.h", "avg_pool2d_backward.h", "_test_serialization_subcmul_ops.h", "max_pool2d_with_indices_ops.h", "dynamic_ir.h", "safe_numerics.h", "special_modified_bessel_i1_native.h", "quantized_max_pool3d_native.h", "_sparse_compressed_tensor_unsafe_native.h", "special_bessel_y1_ops.h", "python_legacy_variable.h", "_lstm_mps_ops.h", "special_airy_ai_native.h", "QuantUtils.h", "_nested_select_backward.h", "conj_native.h", "_foreach_addcmul_native.h", "special_log_softmax_compositeimplicitautograd_dispatch.h", "range_compositeexplicitautograd_dispatch.h", "special_airy_ai_ops.h", "CUDAStream.h", "corrcoef_native.h", "LinearAlgebraUtils.h", "arctanh_ops.h", "is_inference_native.h", "glu_backward_ops.h", "not_equal.h", "_cudnn_rnn_ops.h", "parse_bytecode.h", "upsample_nearest2d_backward_ops.h", "adaptive_max_pool2d.h", "group_norm_compositeimplicitautograd_dispatch.h", "fft_ifftn_compositeimplicitautograd_dispatch.h", "_fused_dropout_ops.h", "arange_compositeexplicitautograd_dispatch.h", "_choose_qparams_per_tensor_native.h", "_foreach_log_ops.h", "CUDADataType.h", "import_export_helpers.h", "_cdist_forward_cuda_dispatch.h", "nansum_cpu_dispatch.h", "_pin_memory_native.h", "adaptive_max_pool1d_native.h", "ir_visitor.h", "embedding.h", "logical_and_ops.h", "scatter_ops.h", "is_inference_ops.h", "msort_ops.h", "_sparse_csr_prod_ops.h", "_upsample_bilinear2d_aa_meta.h", "adaption.h", "cosine_similarity_ops.h", "triangular_solve_ops.h", "unique_dim_native.h", "numa.h", "_foreach_clamp_min_ops.h", "arg.h", "_softmax_backward_data_ops.h", "batch_norm_gather_stats_with_counts_ops.h", "dedup_module_uses.h", "replication_pad1d_meta.h", "put_native.h", "digamma_ops.h", "is_nonzero_native.h", "split_with_sizes.h", "erf_ops.h", "convolution_overrideable_ops.h", "gelu_ops.h", "select_scatter_ops.h", "sgn_meta.h", "cumprod_meta.h", "square_ops.h", "_foreach_expm1_native.h", "Functions.h", "i0.h", "repeat_interleave_ops.h", "flip.h", "_debug_has_internal_overlap_ops.h", "tan_ops.h", "isin_native.h", "StorageImpl.h", "frexp_ops.h", "rsqrt.h", "activation.h", "angle_native.h", "special_multigammaln.h", "vec_base.h", "_foreach_frac_ops.h", "multilabel_margin_loss_forward_ops.h", "_ctc_loss.h", "_pack_padded_sequence_backward_native.h", "tril_indices_ops.h", "upsample_trilinear3d_meta_dispatch.h", "sigmoid_meta.h", "max_pool2d_with_indices_backward_ops.h", "jit.h", "layer_norm_native.h", "log_ops.h", "fused_moving_avg_obs_fake_quant_native.h", "_foreach_reciprocal_native.h", "avg_pool3d_native.h", "unique.h", "histc_ops.h", "linalg_solve_triangular_ops.h", "linalg_eig_native.h", "data_parallel.h", "special_shifted_chebyshev_polynomial_w_ops.h", "allclose_ops.h", "ldexp.h", "is_coalesced_native.h", "nll_loss_nd_ops.h", "_validate_sparse_coo_tensor_args.h", "tensor_qschemes.h", "TorchDispatchModeTLS.h", "normalize_ops.h", "upsample_trilinear3d_compositeexplicitautogradnonfunctional_dispatch.h", "_spdiags.h", "Functions.h", "view_as_complex.h", "new_zeros_compositeexplicitautograd_dispatch.h", "_upsample_bicubic2d_aa_compositeimplicitautograd_dispatch.h", "fmin_meta.h", "peephole_alias_sensitive.h", "softshrink_native.h", "special_erf_native.h", "sum_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_trilinear3d_backward_meta_dispatch.h", "upsample_trilinear3d_ops.h", "dtype_analysis.h", "_triton_multi_head_attention_native.h", "ThreadLocalPythonObjects.h", "randn.h", "lstm_cell_native.h", "hardshrink_backward_ops.h", "Layout.h", "orgqr_ops.h", "cumulative_trapezoid.h", "_prelu_kernel_backward.h", "max_pool2d_backward_native.h", "cpp_intrinsics.h", "rnn_tanh_cell_ops.h", "_foreach_round.h", "max_pool3d_with_indices_backward.h", "pimpl.h", "erfc_ops.h", "addr.h", "max.h", "sqrt_ops.h", "strong_type.h", "to_mkldnn_backward_ops.h", "bernoulli.h", "rot90_native.h", "symbolic_script.h", "python_ivalue.h", "moveaxis_native.h", "upsample_linear1d_backward_cpu_dispatch.h", "rnn.h", "utils.h", "flip_ops.h", "python_fft_functions.h", "linalg_matrix_exp.h", "_functional_sym_constrain_range_compositeexplicitautograd_dispatch.h", "Pow.h", "lu_unpack_ops.h", "crow_indices.h", "_nested_view_from_buffer_copy.h", "renorm_native.h", "tanh_backward_meta.h", "_addmm_activation.h", "_fused_dropout_native.h", "logit_backward_compositeexplicitautogradnonfunctional_dispatch.h", "fwd_decls.h", "relu6.h", "_prelu_kernel_native.h", "Macros.h", "as_strided_copy_native.h", "std_mean_ops.h", "geometric_cuda_dispatch.h", "huber_loss.h", "structseq.h", "_sparse_csr_prod_native.h", "_sparse_sparse_matmul_ops.h", "MPSGuardImpl.h", "_upsample_bicubic2d_aa_cuda_dispatch.h", "masked_select.h", "special_shifted_chebyshev_polynomial_v_meta.h", "is_set_to.h", "glu_backward_jvp_ops.h", "is_leaf_native.h", "special_logit_compositeimplicitautograd_dispatch.h", "lift_closures.h", "fft_fft2.h", "randperm_cpu_dispatch.h", "List.h", "mkldnn_reorder_conv2d_weight.h", "gt_ops.h", "quantized_max_pool2d.h", "glu.h", "var_mean_cuda_dispatch.h", "mv_native.h", "view_as_real.h", "sigmoid_backward_meta.h", "linalg_svdvals_ops.h", "pixel_unshuffle_native.h", "einsum_native.h", "upsample_nearest1d_backward_native.h", "DynamicLayer.h", "aminmax_meta_dispatch.h", "step_lr.h", "special_psi_ops.h", "log_softmax_ops.h", "_copy_from.h", "RedispatchFunctions.h", "nll_loss_forward_meta.h", "bitwise_or_meta.h", "ts_node_lowering.h", "cumulative_trapezoid_ops.h", "graph_fuser.h", "as_strided_copy.h", "conv3d_compositeimplicitautograd_dispatch.h", "record_function.h", "le_meta.h", "SpmmReduceKernel.h", "_nested_tensor_strides_native.h", "masked_select_native.h", "inductor_ops.h", "bitwise_not_meta.h", "values.h", "cpp_hook.h", "PyHandleCache.h", "_test_check_tensor.h", "gcd.h", "linear_compositeimplicitautograd_dispatch.h", "_functional_assert_async.h", "linalg_cholesky_ex.h", "special_bessel_y1_meta.h", "retain_grad.h", "chalf_native.h", "linalg_matrix_norm.h", "check_strict_fusion.h", "deg2rad_native.h", "hann_window_compositeexplicitautograd_dispatch.h", "_conv_depthwise2d.h", "_to_sparse_native.h", "special_exp2_ops.h", "upsample_nearest3d_cuda_dispatch.h", "copysign.h", "scatter.h", "to_sparse_csr_native.h", "native_dropout_cpu_dispatch.h", "greater.h", "MPSAllocatorInterface.h", "random_meta_dispatch.h", "_weight_norm_interface_native.h", "unfold_ops.h", "add_meta.h", "_fft_c2c_ops.h", "binary_cross_entropy_ops.h", "Event.h", "request_callback_impl.h", "type_caster_base.h", "log_softmax_compositeimplicitautograd_dispatch.h", "sparse_sampled_addmm.h", "_pdist_forward_native.h", "unfold_native.h", "diagflat.h", "record_function_ops.h", "mkldnn_max_pool3d.h", "cumsum_cpu_dispatch.h", "put.h", "bitwise_left_shift_meta.h", "linalg_lu_factor_ops.h", "isclose_native.h", "randperm.h", "TypeIndex.h", "Context.h", "python_arg_flatten.h", "bincount_cuda_dispatch.h", "exp2_ops.h", "i0_meta.h", "linear.h", "_to_sparse_bsr_ops.h", "_pin_memory_compositeexplicitautograd_dispatch.h", "hardtanh_ops.h", "fft_fftn_native.h", "SymNodeImpl.h", "python_functions.h", "_embedding_bag.h", "_remove_batch_dim_native.h", "unpickler.h", "_to_sparse_csr_ops.h", "avg_pool2d_meta_dispatch.h", "_efficient_attention_forward_cuda_dispatch.h", "any_value.h", "native_layer_norm_cpu_dispatch.h", "CUDAHooks.h", "utils.h", "fake_quantize_per_channel_affine.h", "vec.h", "as_strided_scatter_ops.h", "upsample_nearest1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "kernel.h", "randn_like_compositeimplicitautogradnestedtensor_dispatch.h", "det_ops.h", "feature_dropout_ops.h", "cholesky_solve_ops.h", "avg_pool3d_backward_meta_dispatch.h", "full_like_compositeexplicitautograd_dispatch.h", "accumulate_grad.h", "_unpack_dual_ops.h", "tensorpipe_utils.h", "linalg_vector_norm_meta.h", "leaky_relu.h", "glu_ops.h", "special_shifted_chebyshev_polynomial_w_meta.h", "cosh_meta.h", "arctan.h", "miopen_depthwise_convolution_ops.h", "pybind11.h", "isclose_ops.h", "irparser.h", "relu6_ops.h", "select_backward_native.h", "random_compositeexplicitautograd_dispatch.h", "to_native.h", "native_batch_norm_ops.h", "mkldnn_max_pool3d_backward_ops.h", "memory_dag.h", "neg_native.h", "vec512_double.h", "ones_native.h", "_transformer_encoder_layer_fwd_ops.h", "mkldnn_reorder_conv3d_weight_native.h", "embedding_bag.h", "sparse_csc_tensor_native.h", "_conj_native.h", "ir.h", "_thnn_fused_lstm_cell_backward_impl_ops.h", "conv_depthwise3d_native.h", "threshold_backward_native.h", "cudnn_convolution_add_relu_compositeexplicitautograd_dispatch.h", "cudnn_affine_grid_generator_backward.h", "bilinear_compositeimplicitautograd_dispatch.h", "IsContiguous.h", "_transform_bias_rescale_qkv.h", "_foreach_atan_native.h", "dequantize.h", "_upsample_bicubic2d_aa_backward.h", "_embedding_bag_native.h", "map.h", "_thnn_differentiable_gru_cell_backward_compositeimplicitautograd_dispatch.h", "is_conj_native.h", "reflection_pad3d_ops.h", "_shape_as_tensor_ops.h", "special_chebyshev_polynomial_u.h", "frac_meta.h", "requires_grad_ops.h", "logspace_compositeexplicitautograd_dispatch.h", "_thnn_fused_lstm_cell_backward_ops.h", "moments_utils.h", "_foreach_add_ops.h", "index_meta_dispatch.h", "_sample_dirichlet_cpu_dispatch.h", "special_laguerre_polynomial_l.h", "adaptive_max_pool3d_meta.h", "mode_native.h", "ts_eager_fallback.h", "_linalg_det_ops.h", "cleanup_autograd_context_resp.h", "fractional_max_pool2d_native.h", "_linalg_eigh.h", "tan_meta.h", "log1p_meta.h", "BatchRulesHelper.h", "is_pinned.h", "mkldnn_max_pool3d_backward_native.h", "upsample_nearest1d_compositeimplicitautograd_dispatch.h", "special_chebyshev_polynomial_t_ops.h", "sub_ops.h", "_flash_attention_forward_native.h", "bailout_graph.h", "trapezoid_ops.h", "gather_backward.h", "pixelshuffle.h", "log2_meta.h", "vec256_qint8_vsx.h", "autograd_metadata.h", "empty_strided.h", "_upsample_bicubic2d_aa_cpu_dispatch.h", "HIPHooksInterface.h", "sym_constrain_range.h", "quantize_per_channel_native.h", "nll_loss_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_convolution.h", "tree_views.h", "q_scale_ops.h", "_functional_sym_constrain_range.h", "_softmax_backward_data_native.h", "floor_meta.h", "mean_native.h", "rename.h", "upsample_linear1d_backward.h", "mkldnn_linear_backward_native.h", "fft_fftshift_native.h", "ne_ops.h", "_to_sparse_semi_structured_ops.h", "graph_opt.h", "prod_cuda_dispatch.h", "isnan_native.h", "special_chebyshev_polynomial_u_native.h", "grid_sampler_2d_backward_native.h", "upsample_nearest1d_backward_meta.h", "CPUApplyUtils.h", "ScalarTypeToTypeMeta.h", "isneginf_ops.h", "histogramdd.h", "dataloader_options.h", "SymBool.h", "_coalesced_native.h", "activation.h", "upsampling.h", "_upsample_nearest_exact1d_compositeexplicitautogradnonfunctional_dispatch.h", "slow_conv3d_forward_ops.h", "ccol_indices_copy_ops.h", "nextafter_native.h", "_pin_memory.h", "poisson_compositeexplicitautograd_dispatch.h", "CheckMemoryFormat.h", "linalg_slogdet_native.h", "masked_select_backward_ops.h", "conv1d.h", "fft_fftshift_compositeimplicitautograd_dispatch.h", "special_gammainc_ops.h", "_sobol_engine_draw_ops.h", "roll_ops.h", "layer_norm.h", "_conj_copy.h", "empty_like_native.h", "fbgemm_linear_fp16_weight_fp32_activation_ops.h", "linalg_vector_norm_native.h", "to_sparse_bsc_native.h", "indices_ops.h", "stride.h", "sum_meta.h", "batch_norm_update_stats_compositeexplicitautograd_dispatch.h", "view_as_complex_native.h", "le_ops.h", "_upsample_bilinear2d_aa_backward_ops.h", "upsample_nearest1d_ops.h", "adaptive_avg_pool1d_ops.h", "add.h", "slow_conv_transpose2d_cpu_dispatch.h", "unique_name_manager.h", "input_metadata.h", "special_modified_bessel_k1.h", "_upsample_nearest_exact1d_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_w_native.h", "prod_native.h", "script_call.h", "cosine_similarity_native.h", "_fused_adam_native.h", "_linalg_solve_ex_native.h", "Array.h", "bitwise_or_ops.h", "_foreach_log10_native.h", "_empty_per_channel_affine_quantized_compositeexplicitautograd_dispatch.h", "atleast_3d_ops.h", "EmbeddingPackedParams.h", "_foreach_trunc_native.h", "unflatten.h", "im2col_native.h", "view_ops.h", "randn_like_native.h", "_cufft_get_plan_cache_size_ops.h", "q_per_channel_zero_points.h", "reshape_as_native.h", "GeneratorImpl.h", "mps_convolution_transpose_backward_ops.h", "QScheme.h", "replacement_of_old_operators.h", "clamp_meta_dispatch.h", "_log_softmax_ops.h", "_foreach_zero_native.h", "pad_sequence.h", "collection.h", "item_ops.h", "socket.h", "_fake_quantize_learnable_per_channel_affine_ops.h", "type_as_native.h", "_make_dep_token.h", "special_zeta.h", "remove_inplace_ops.h", "mkldnn_rnn_layer_backward_compositeexplicitautograd_dispatch.h", "cummax.h", "operator.h", "python_linalg_functions.h", "_stack_native.h", "PyObjectSlot.h", "_foreach_sqrt_ops.h", "empty_ops.h", "miopen_batch_norm_cuda_dispatch.h", "miopen_convolution_transpose_cuda_dispatch.h", "back_compat.h", "select_scatter.h", "mkldnn_adaptive_avg_pool2d.h", "special_bessel_y0_native.h", "eliminate_no_ops.h", "MPSDevice.h", "_test_check_tensor_native.h", "vec512_complex_double.h", "hardshrink_ops.h", "exponential.h", "_ctc_loss_backward_ops.h", "special_logsumexp_native.h", "avg_pool2d_backward_meta_dispatch.h", "matmul.h", "rpc_with_autograd.h", "_cdist_forward_cpu_dispatch.h", "special_scaled_modified_bessel_k0.h", "_mps_convolution_transpose_ops.h", "new_full.h", "fmin_ops.h", "std_native.h", "cat_native.h", "embedding.h", "tensordot_ops.h", "mini_environment.h", "batch_norm_backward_reduce_ops.h", "rnn_tanh_cell.h", "_functions.h", "subgraph_utils.h", "_sparse_bsc_tensor_unsafe.h", "minimum_meta.h", "sparse_mask.h", "_to_cpu_ops.h", "nll_loss_backward.h", "sparse_bsc_tensor_compositeimplicitautograd_dispatch.h", "nanquantile_compositeimplicitautograd_dispatch.h", "promote_types_ops.h", "base.h", "convert_to_ssa.h", "argmax_ops.h", "mkldnn_linear_backward_input_ops.h", "_upsample_bilinear2d_aa_backward_cpu_dispatch.h", "take_along_dim_compositeimplicitautograd_dispatch.h", "native_group_norm_backward_cuda_dispatch.h", "polar_ops.h", "sparse_dim_ops.h", "common.h", "external_functions.h", "LocalDispatchKeySet.h", "CatKernel.h", "adaptive_max_pool2d_native.h", "arcsin_ops.h", "special_i1.h", "vec512.h", "hardswish_backward_native.h", "restore_mutation.h", "print_handler.h", "grid_sampler_3d_ops.h", "upsample_nearest2d.h", "_cufft_get_plan_cache_max_size.h", "batch_norm_stats_native.h", "avg_pool3d_backward_meta.h", "nan_to_num.h", "as_strided_copy_compositeexplicitautograd_dispatch.h", "ge_meta.h", "pooling.h", "fold_conv_bn.h", "geqrf_ops.h", "reflection_pad1d_meta.h", "_has_same_storage_numel_ops.h", "fft_ifft2_compositeimplicitautograd_dispatch.h", "_remove_batch_dim.h", "_foreach_sign_native.h", "polar.h", "nll_loss2d_native.h", "ThreadLocalState.h", "special_expit.h", "rnn_tanh_native.h", "_aminmax_ops.h", "_transformer_encoder_layer_fwd.h", "slow_conv_dilated3d_ops.h", "_sparse_csc_tensor_unsafe_compositeimplicitautograd_dispatch.h", "_transformer_encoder_layer_fwd_cuda_dispatch.h", "slow_conv_transpose3d_ops.h", "_local_scalar_dense_ops.h", "special_hermite_polynomial_he_native.h", "special_erfinv_native.h", "init.h", "special_expm1_ops.h", "resize_as.h", "isneginf_meta.h", "sparse_resize_and_clear_ops.h", "linalg_diagonal_ops.h", "leaky_relu_ops.h", "embedding_renorm_native.h", "special_erfc_ops.h", "profiler_edge.h", "_efficientzerotensor_ops.h", "nll_loss2d_ops.h", "_thnn_differentiable_lstm_cell_backward.h", "SafePyObject.h", "native_batch_norm_backward_cuda_dispatch.h", "_transformer_encoder_layer_fwd_native.h", "rnn_tanh_cell_compositeimplicitautograd_dispatch.h", "fft_rfftn.h", "upsample_bicubic2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "MaxPooling.h", "atleast_3d.h", "_masked_softmax_backward_compositeexplicitautograd_dispatch.h", "logical_xor_native.h", "native_layer_norm_cuda_dispatch.h", "randperm_compositeexplicitautograd_dispatch.h", "_sparse_csc_tensor_unsafe_ops.h", "MaxUnpoolKernel.h", "replication_pad2d_meta.h", "to_dense.h", "reflection_pad2d_backward.h", "mkldnn_max_pool2d_native.h", "fft_ifftshift_native.h", "edge.h", "special_chebyshev_polynomial_v.h", "kaiser_window.h", "select_ops.h", "fft_fftfreq_native.h", "native_layer_norm_backward_native.h", "_upsample_nearest_exact1d_backward.h", "cosh_native.h", "randperm_native.h", "atleast_1d_ops.h", "_nested_from_padded_native.h", "SymFloat.h", "narrow_native.h", "linalg_matrix_norm_compositeimplicitautograd_dispatch.h", "ParallelNative.h", "replication_pad1d_native.h", "conv_transpose1d_compositeimplicitautograd_dispatch.h", "special_erf.h", "matrix_exp_backward_native.h", "_softmax_backward_data.h", "moveaxis.h", "_standard_gamma_native.h", "special_expm1.h", "linalg_vecdot_ops.h", "_sobol_engine_draw.h", "_masked_softmax_backward_ops.h", "_foreach_expm1_ops.h", "Utils.h", "aminmax_meta.h", "bitwise_not_native.h", "Float8_e4m3fn-inl.h", "fft_hfftn_ops.h", "avg_pool2d_native.h", "avg_pool2d_cpu_dispatch.h", "arange.h", "choose_qparams_optimized.h", "upsample_nearest1d_backward_cpu_dispatch.h", "loop_unrolling.h", "_to_sparse_cpu_dispatch.h", "soft_margin_loss_backward_native.h", "_sparse_sum_native.h", "_reshape_alias_ops.h", "Vitals.h", "repeat_interleave_compositeexplicitautograd_dispatch.h", "_nested_view_from_buffer.h", "linalg_pinv.h", "erf.h", "xor_ops.h", "to_ops.h", "exp2_native.h", "tril_indices_cuda_dispatch.h", "addcmul.h", "det.h", "fft_ihfft2.h", "Dtype.h", "_foreach_norm_cuda_dispatch.h", "mkldnn_max_pool3d_ops.h", "unique_consecutive_cpu_dispatch.h", "ir_mutator.h", "upsample_bicubic2d_backward_cuda_dispatch.h", "fft_hfftn_compositeimplicitautograd_dispatch.h", "_slow_conv2d_backward_ops.h", "vstack.h", "jit_trace.h", "_foreach_lgamma_ops.h", "resolve_conj.h", "binomial_cpu_dispatch.h", "replication_pad3d_backward_ops.h", "mkldnn_reorder_conv2d_weight_ops.h", "python_list.h", "Exceptions.h", "TensorOperators.h", "special_spherical_bessel_j0_meta.h", "_upsample_nearest_exact1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "var_cuda_dispatch.h", "ir_builder.h", "stft_compositeimplicitautograd_dispatch.h", "slice_ops.h", "eval_frame.h", "miopen_convolution_transpose_ops.h", "native_group_norm_ops.h", "python_torch_function_mode.h", "cudnn_convolution.h", "clamp_ops.h", "unique_dim_consecutive_ops.h", "graph_task.h", "_nested_tensor_softmax_with_shape.h", "q_scale_native.h", "eye_native.h", "values_ops.h", "mish_meta.h", "softmax_native.h", "linalg_pinv_native.h", "_pack_padded_sequence_native.h", "rrelu.h", "upsample_linear1d_native.h", "special_chebyshev_polynomial_v_meta.h", "slice_backward_native.h", "_propagate_xla_data_ops.h", "vec256_quint8_vsx.h", "batch_norm_gather_stats.h", "norm_cpu_dispatch.h", "native_layer_norm_native.h", "linalg_matmul_native.h", "special_scaled_modified_bessel_k1.h", "module_python.h", "flatten_dense_tensors_native.h", "decomposition_registry.h", "import_read.h", "init_qnnpack.h", "dead_code_elimination.h", "upsample_nearest3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_solve_ex_native.h", "_convert_indices_from_csr_to_coo_native.h", "new_full_ops.h", "_cudnn_rnn_cuda_dispatch.h", "linalg_svdvals.h", "cumprod_native.h", "amax_meta.h", "special_log_softmax_ops.h", "hardshrink_backward_native.h", "_pdist_forward.h", "logit_backward_ops.h", "flipud.h", "sparse_compressed_tensor_compositeexplicitautograd_dispatch.h", "_compute_linear_combination_ops.h", "gcd_ops.h", "cross_entropy_loss_native.h", "special_shifted_chebyshev_polynomial_t_native.h", "copy_sparse_to_sparse.h", "empty_native.h", "bitwise_not_ops.h", "mm_meta.h", "_has_compatible_shallow_copy_type.h", "copy.h", "cauchy_meta_dispatch.h", "sinc_native.h", "special_gammaincc.h", "eq.h", "_foreach_addcdiv.h", "index_select_backward.h", "triu_indices_ops.h", "optimization_utils.h", "_sparse_csr_tensor_unsafe_ops.h", "_has_same_storage_numel.h", "topk_native.h", "_upsample_bicubic2d_aa.h", "clamp_min_native.h", "dist_ops.h", "sort_compositeexplicitautogradnonfunctional_dispatch.h", "batch_norm_backward_elemt_compositeexplicitautograd_dispatch.h", "chain_matmul_ops.h", "jit_type.h", "Allocator.h", "WrapDimUtils.h", "asin_meta.h", "_cast_Byte_ops.h", "_foreach_sub_ops.h", "to_sparse_csr.h", "normal_cuda_dispatch.h", "matrix_H_native.h", "StreamGuard.h", "var_native.h", "view_as.h", "cpp_custom_type_hack.h", "NativeMetaFunction.h", "sparse_bsr_tensor_native.h", "_sparse_sum_backward_native.h", "_thnn_fused_gru_cell_backward_native.h", "_sparse_csc_tensor_unsafe_native.h", "values_native.h", "matrix_H.h", "linalg_lu_solve_native.h", "softplus_backward_ops.h", "special_entr_meta.h", "isposinf_native.h", "_nested_tensor_strides.h", "fake_quantize_per_tensor_affine_cachemask_native.h", "instance_norm.h", "neg_meta.h", "equal_native.h", "_segment_reduce_backward_cpu_dispatch.h", "_ctc_loss_native.h", "operator_options.h", "_fused_sdp_choice_cuda_dispatch.h", "resize_cpu_dispatch.h", "random_cuda_dispatch.h", "_triton_scaled_dot_attention_native.h", "im2col_shape_check.h", "cudnn_convolution_add_relu_native.h", "special_log_softmax_native.h", "op_registry.h", "new_empty_strided_compositeexplicitautogradnonfunctional_dispatch.h", "int128.h", "transformercoder.h", "cumsum_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_compressed_tensor_unsafe_compositeimplicitautograd_dispatch.h", "unsqueeze_copy_ops.h", "masked_fill_native.h", "ExpandUtils.h", "asinh_ops.h", "avg_pool3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "reciprocal_meta.h", "order_preserving_flat_hash_map.h", "_empty_per_channel_affine_quantized_cpu_dispatch.h", "_sparse_addmm_ops.h", "OperatorKernel.h", "_foreach_clamp_max.h", "multilabel_margin_loss_ops.h", "_foreach_neg_native.h", "native_layer_norm_ops.h", "external_functions_core.h", "upsample_bicubic2d_ops.h", "unfold_copy.h", "backend_resolver.h", "unique_consecutive_compositeexplicitautograd_dispatch.h", "huber_loss_native.h", "feature_alpha_dropout_native.h", "threshold_backward_ops.h", "quantized_rnn_relu_cell_native.h", "_reshape_alias_native.h", "cudnn_is_acceptable_native.h", "mps_convolution_backward_native.h", "_empty_affine_quantized.h", "leaky_relu_native.h", "fmin.h", "multi_margin_loss_backward_ops.h", "split_copy_native.h", "celu_ops.h", "absolute_ops.h", "cross_entropy_loss.h", "sigmoid_backward.h", "tanh.h", "python.h", "env.h", "_thnn_fused_gru_cell_cuda_dispatch.h", "upsample_linear1d_cuda_dispatch.h", "align_as_ops.h", "detach_copy_native.h", "_cummax_helper.h", "_upsample_bilinear2d_aa_backward_compositeexplicitautogradnonfunctional_dispatch.h", "batch_mm.h", "_fft_r2c.h", "nuclear_norm.h", "bincount_cpu_dispatch.h", "as_strided_cuda_dispatch.h", "threshold_ops.h", "linalg_diagonal_native.h", "_embedding_bag_backward_ops.h", "native_batch_norm.h", "pairwise_distance_native.h", "record_stream_native.h", "_histogramdd_bin_edges_compositeexplicitautograd_dispatch.h", "_backward_native.h", "insert_observers.h", "linalg_lu.h", "_native_multi_head_attention_cpu_dispatch.h", "_has_compatible_shallow_copy_type_native.h", "quantization_patterns.h", "addr_ops.h", "resize_ops.h", "CUDAGraphsC10Utils.h", "_validate_sparse_coo_tensor_args_native.h", "_validate_sparse_csc_tensor_args_native.h", "_slow_conv2d_forward_cuda_dispatch.h", "_sparse_coo_tensor_with_dims.h", "nll_loss_backward_cuda_dispatch.h", "random_ops.h", "backend_data.h", "new_ones_native.h", "max_unpool2d_native.h", "external_functions_registry.h", "bounds_inference.h", "_foreach_clamp_min_native.h", "_thnn_fused_lstm_cell_backward_compositeimplicitautograd_dispatch.h", "_efficientzerotensor_meta_dispatch.h", "_new_zeros_with_same_feature_meta_native.h", "_test_optional_intlist_native.h", "linalg_solve_triangular_native.h", "_thnn_differentiable_lstm_cell_backward_native.h", "_linalg_solve_ex.h", "acos_ops.h", "mkldnn_linear_ops.h", "cat_ops.h", "var_mean.h", "alias_analysis.h", "python_tracer.h", "_foreach_norm_native.h", "fake_quantize_per_channel_affine_ops.h", "_softmax_ops.h", "_autocast_to_reduced_precision_native.h", "softshrink_backward_native.h", "_adaptive_avg_pool3d_backward_ops.h", "row_stack_ops.h", "_make_dep_token_native.h", "_foreach_cos.h", "addbmm.h", "_reshape_copy_ops.h", "data_flow.h", "exceptions.h", "bernoulli_native.h", "_segment_reduce_backward_compositeexplicitautograd_dispatch.h", "_unique2_ops.h", "fft_hfftn_native.h", "affine_grid_generator_native.h", "ir_printer.h", "hardswish_native.h", "_fused_adamw_cuda_dispatch.h", "arithmetic_ir_ops.h", "vec512_qint.h", "TorchDispatchUtils.h", "special_gammaincc_native.h", "_gather_sparse_backward_native.h", "miopen_batch_norm_ops.h", "slow_conv_dilated3d_cpu_dispatch.h", "alias_copy_native.h", "greater_ops.h", "_efficient_attention_forward.h", "take_ops.h", "linear_native.h", "rnn_tanh_cell_native.h", "_fused_adamw_ops.h", "special_shifted_chebyshev_polynomial_t_meta.h", "_thnn_fused_gru_cell_ops.h", "_pack_padded_sequence_ops.h", "_unsafe_index.h", "log1p_native.h", "_functional_assert_async_native.h", "special_ndtri_meta.h", "onnx.h", "_logcumsumexp_native.h", "clear_profiling.h", "_dimI_native.h", "hypot_meta.h", "var_substitutor.h", "fake_quantize_per_tensor_affine_cachemask_ops.h", "instance_norm_ops.h", "_embedding_bag_forward_only.h", "mvlgamma.h", "std_mean_native.h", "native_group_norm_backward_ops.h", "concrete_module_type.h", "native_layer_norm_backward_cuda_dispatch.h", "_batch_norm_impl_index_backward_compositeimplicitautograd_dispatch.h", "logaddexp_meta.h", "rand_native.h", "dropout.h", "upsample_nearest1d_meta.h", "lift_fresh_native.h", "adaptive_avg_pool2d_native.h", "inline_container.h", "import_export_constants.h", "_fused_sdp_choice_meta_dispatch.h", "_test_autograd_multiple_dispatch_view_copy_native.h", "pybind.h", "_adaptive_avg_pool2d_backward.h", "_mkldnn_transpose.h", "linalg_householder_product_ops.h", "rshift.h", "index_ops.h", "slow_conv_dilated2d.h", "_efficient_attention_backward.h", "cudnn_batch_norm_backward.h", "Bitset.h", "numpy_T_native.h", "python_arg_parsing.h", "decompose_ops.h", "trunc_ops.h", "upsample_bilinear2d_native.h", "accumulate.h", "q_per_channel_axis_native.h", "aminmax.h", "select_native.h", "vulkan_rewrite.h", "native_batch_norm_backward_compositeexplicitautograd_dispatch.h", "_version_native.h", "as_strided_cpu_dispatch.h", "arctan2_native.h", "_coalesce_native.h", "conv.h", "special_i0e_native.h", "fake_quantize_per_channel_affine_cachemask_backward_ops.h", "nonzero_numpy_native.h", "slow_conv_dilated2d_compositeexplicitautograd_dispatch.h", "quantized_rnn_relu_cell_ops.h", "special_exp2.h", "special_bessel_y1_native.h", "VariableType.h", "ir_util.h", "_sparse_log_softmax_backward_data_ops.h", "tensor_split_ops.h", "ctc_loss.h", "miopen_convolution_add_relu_ops.h", "_convert_indices_from_coo_to_csr_ops.h", "fft_fftfreq_ops.h", "record_stream.h", "random.h", "_log_softmax_native.h", "multinomial_native.h", "_foreach_sub_native.h", "avg_pool2d.h", "tensor_split_native.h", "native_norm.h", "swapdims_ops.h", "_embedding_bag_per_sample_weights_backward.h", "sum_ops.h", "_foreach_abs.h", "flatbuffer_loader.h", "_masked_scale.h", "_functional_sym_constrain_range_for_size.h", "exp_native.h", "TensorCompare.h", "grid_sampler_3d_native.h", "xnnpack_rewrite.h", "sigmoid_backward_native.h", "tensordot.h", "OperatorOptions.h", "real_ops.h", "bitwise_or.h", "CUDAMathCompat.h", "conv_transpose3d_ops.h", "_pad_enum_ops.h", "backend_interface.h", "cudnn_grid_sampler_ops.h", "_index_put_impl_ops.h", "frozen_graph_optimizations.h", "subtract_native.h", "index_compositeexplicitautogradnonfunctional_dispatch.h", "is_coalesced.h", "sinc_meta.h", "_upsample_nearest_exact2d_backward_meta.h", "_batch_norm_impl_index_ops.h", "tensor_numpy.h", "multi_margin_loss_native.h", "linalg_lu_factor_ex_native.h", "_cast_Float_ops.h", "cuda_codegen.h", "index_meta.h", "SparseCsrTensorImpl.h", "rshift_native.h", "linalg_multi_dot.h", "TensorModeKernel.h", "mvlgamma_native.h", "_test_autograd_multiple_dispatch_view.h", "fft_irfft.h", "prim_ops_registery.h", "_functional_sym_constrain_range_for_size_ops.h", "_autocast_to_reduced_precision_ops.h", "blob.h", "igammac_meta.h", "_scaled_dot_product_flash_attention_backward_ops.h", "batch_norm_elemt_ops.h", "Handle.h", "linalg_householder_product_native.h", "_nested_tensor_size.h", "rpc_with_profiling_resp.h", "fbgemm_pack_quantized_matrix.h", "arcsinh.h", "source_range_serialization_impl.h", "nll_loss2d_forward.h", "greater_native.h", "embedding_dense_backward_native.h", "hardtanh.h", "fft_fftfreq.h", "_upsample_nearest_exact3d_backward_cpu_dispatch.h", "mse_loss_native.h", "slogdet_ops.h", "create_autodiff_subgraphs.h", "_cdist_forward_native.h", "one_hot_ops.h", "linalg_inv_native.h", "_values_copy.h", "clip.h", "lcm_native.h", "index_put.h", "cartesian_prod.h", "soft_margin_loss_native.h", "_foreach_sqrt_native.h", "greater_equal_native.h", "type_ptr.h", "linalg_inv_ops.h", "slice_indices_adjust.h", "pdist.h", "convolution_compositeexplicitautograd_dispatch.h", "_standard_gamma_grad_ops.h", "clip_ops.h", "MemoryFormat.h", "avg_pool3d_backward.h", "min_native.h", "softshrink_backward_ops.h", "gt_meta.h", "python_hook.h", "reflection_pad3d_meta.h", "as_strided_scatter_compositeexplicitautograd_dispatch.h", "bucketize_native.h", "scatter_native.h", "Resize.h", "function.h", "squeeze.h", "conv_transpose1d_native.h", "split_with_sizes_native.h", "elu_ops.h", "replication_pad1d_backward.h", "_foreach_exp_native.h", "diag_native.h", "_triton_multi_head_attention.h", "_thnn_fused_gru_cell_backward_ops.h", "device_set.h", "serialize.h", "_nested_tensor_from_tensor_list_ops.h", "index_add_native.h", "variadic_ops.h", "promote_types.h", "atan2_meta.h", "_sparse_compressed_tensor_unsafe.h", "Formatting.h", "mul.h", "batch_norm_stats.h", "cumsum.h", "index_add_ops.h", "index_cuda_dispatch.h", "searchsorted.h", "atleast_2d_ops.h", "version.h", "softmax_compositeexplicitautograd_dispatch.h", "is_complex.h", "graph_utils.h", "slow_conv_dilated2d_ops.h", "schema_matching.h", "_upsample_nearest_exact1d_backward_cpu_dispatch.h", "to_mkldnn_backward.h", "logcumsumexp_ops.h", "sgn_ops.h", "_make_dual_copy_native.h", "soft_margin_loss_ops.h", "nan_to_num_ops.h", "_test_ambiguous_defaults_native.h", "diagflat_ops.h", "can_cast_native.h", "lu_solve_ops.h", "_upsample_nearest_exact2d_backward_native.h", "isnan_ops.h", "_add_batch_dim.h", "svd_ops.h", "fft_rfftn_compositeimplicitautograd_dispatch.h", "fft_ifftshift_compositeimplicitautograd_dispatch.h", "fft_rfftfreq_native.h", "bitwise_not.h", "corrcoef_ops.h", "sign_native.h", "_unpack_dual_native.h", "as_strided_copy_ops.h", "heaviside.h", "_upsample_nearest_exact2d_backward_meta_dispatch.h", "mps.h", "mean_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_bilinear2d_meta_dispatch.h", "special_erfinv_ops.h", "special_zeta_meta.h", "silu_backward.h", "argsort_ops.h", "std_mean_compositeexplicitautograd_dispatch.h", "cudnn_affine_grid_generator_backward_ops.h", "diagonal_copy_native.h", "_foreach_zero_ops.h", "masked_scatter_native.h", "cudnn_grid_sampler_backward_ops.h", "unsafe_chunk_ops.h", "acos_native.h", "WrapFunctionIntoRuntimeFunctor.h", "nonzero_ops.h", "grid_sampler_2d_backward_ops.h", "_upsample_bilinear2d_aa_backward_meta_dispatch.h", "mkldnn_rnn_layer_backward_ops.h", "upsample_nearest2d_compositeimplicitautograd_dispatch.h", "special_xlogy_native.h", "_cufft_get_plan_cache_size_native.h", "sparse_bsr_tensor_ops.h", "_is_any_true_native.h", "_fft_c2c_native.h", "linalg_vander.h", "cumprod_backward_native.h", "NamedTensor.h", "_scaled_mm_ops.h", "fractional_max_pool2d_meta.h", "special_erfcx.h", "erf_meta.h", "upsample_nearest1d_native.h", "promoted_prim_ops.h", "upsample_linear1d_backward_cuda_dispatch.h", "_convolution_compositeexplicitautograd_dispatch.h", "batchnorm.h", "_is_all_true_native.h", "pow_meta.h", "log1p.h", "slice_scatter_native.h", "subgraph_rewrite.h", "fmod.h", "_autocast_to_full_precision.h", "mkldnn_max_pool3d_native.h", "miopen_batch_norm_backward_cuda_dispatch.h", "sub_meta.h", "embedding_bag_compositeimplicitautograd_dispatch.h", "cast.h", "NativeFunction.h", "loss.h", "native_norm_ops.h", "NestedTensorImpl.h", "zeros_like_compositeimplicitautogradnestedtensor_dispatch.h", "_nested_from_padded_and_nested_example.h", "_foreach_erfc_ops.h", "nll_loss_forward_cuda_dispatch.h", "diff_compositeimplicitautograd_dispatch.h", "_standard_gamma_grad.h", "_adaptive_avg_pool3d.h", "kron_ops.h", "_fft_c2r.h", "qr_native.h", "_dirichlet_grad_ops.h", "asin.h", "_cast_Double.h", "index_reduce_meta.h", "hardshrink_backward_meta.h", "max_pool3d.h", "argmax_meta.h", "_pad_circular_native.h", "pybind_utils.h", "lstm_mps_backward_native.h", "reflection_pad3d_backward_native.h", "empty_like.h", "stft_native.h", "mT_ops.h", "view_as_real_copy_ops.h", "string_utils.h", "_native_batch_norm_legit.h", "annotate_warns.h", "DepthwiseConvKernel.h", "nonzero_static.h", "nested_to_padded_tensor_native.h", "_upsample_nearest_exact2d_cuda_dispatch.h", "ForeachUtils.h", "node_hashing.h", "vander_native.h", "rpc.h", "_pdist_backward_ops.h", "_weight_norm.h", "acos_meta.h", "MemoryFormat.h", "var_mean_compositeexplicitautograd_dispatch.h", "matrix_power_native.h", "hardsigmoid_ops.h", "copysign_meta.h", "linalg_tensorinv_native.h", "upsample_nearest3d_meta.h", "rref_interface.h", "smooth_l1_loss_ops.h", "_version.h", "diagonal.h", "replication_pad2d_backward.h", "fft_rfftn_ops.h", "poisson_cpu_dispatch.h", "special_spherical_bessel_j0_native.h", "log_normal_cuda_dispatch.h", "_cast_Long_ops.h", "inline_forked_closures.h", "special_polygamma_native.h", "fft_rfft2.h", "special_softmax_ops.h", "miopen_rnn_backward_native.h", "cudnn_convolution_transpose.h", "_thnn_fused_lstm_cell.h", "flipud_native.h", "mps_convolution_backward.h", "linalg_multi_dot_native.h", "agent_utils.h", "_embedding_bag_cpu_dispatch.h", "prod_meta.h", "align_tensors_native.h", "SmallBuffer.h", "slow_conv_transpose3d.h", "mixed_data_type.h", "mkldnn_adaptive_avg_pool2d_native.h", "sqrt_native.h", "asin_native.h", "tensor_aten_ops.h", "log_sigmoid.h", "BucketizationUtils.h", "addmv_meta.h", "_to_sparse_csc_cuda_dispatch.h", "replication_pad1d_backward_ops.h", "linalg_vector_norm.h", "_sparse_csr_sum_ops.h", "linspace_ops.h", "Utils.h", "_cufft_get_plan_cache_max_size_ops.h", "upsample_nearest3d_backward_cuda_dispatch.h", "huber_loss_backward_native.h", "avg_pool2d_backward_cuda_dispatch.h", "isclose.h", "_has_compatible_shallow_copy_type_ops.h", "ATen_fwd.h", "BinaryOps.h", "cudnn_convolution_transpose_ops.h", "fft_ifftn.h", "prod_compositeexplicitautograd_dispatch.h", "special_log_ndtr_native.h", "gru_cell_native.h", "to_dense_native.h", "special_i1e.h", "InferenceMode.h", "linalg_ldl_solve_meta.h", "_sparse_compressed_tensor_unsafe_ops.h", "torchscript_functions.h", "_upsample_bilinear2d_aa_backward_meta.h", "SymIntArrayRef.h", "_adaptive_avg_pool3d_native.h", "_scaled_dot_product_attention_math_compositeimplicitautograd_dispatch.h", "TensorIteratorInternal.h", "tril_indices_cpu_dispatch.h", "_foreach_neg.h", "TensorBody.h", "selu_ops.h", "new_zeros_ops.h", "gt.h", "_batch_norm_impl_index_backward.h", "sparse_compressed_tensor.h", "linear_ops.h", "engine.h", "complex.h", "vol2col.h", "_scaled_dot_product_efficient_attention_backward_native.h", "_is_all_true.h", "_foreach_abs_native.h", "as_strided_scatter_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_solve_ex.h", "_sparse_softmax_native.h", "miopen_rnn_backward_ops.h", "nanquantile_native.h", "from_file_native.h", "special_erfc_native.h", "grid_sampler_3d_backward_ops.h", "_reshape_alias.h", "cross_entropy_loss_compositeimplicitautograd_dispatch.h", "_add_batch_dim_native.h", "reflection_pad1d_backward.h", "NumericUtils.h", "_masked_softmax.h", "copy_ops.h", "float_power.h", "arccosh.h", "_softmax_native.h", "ReduceOps.h", "min_meta.h", "eye_compositeexplicitautograd_dispatch.h", "lu_solve.h", "or_native.h", "hooks_for_testing.h", "_upsample_nearest_exact1d.h", "_sparse_softmax_backward_data.h", "MaybeOwned.h", "special_hermite_polynomial_h_native.h", "_make_dual_ops.h", "as_strided_native.h", "module.h", "Cross.h", "max_pool3d_native.h", "_unsafe_view.h", "hardshrink_meta.h", "expand_copy_native.h", "_upsample_bilinear2d_aa_cpu_dispatch.h", "transformer.h", "upsample_nearest1d_backward_meta_dispatch.h", "nan_to_num_compositeexplicitautograd_dispatch.h", "linalg_matrix_rank.h", "freeze_module.h", "col2im_native.h", "indices_copy.h", "_is_any_true_ops.h", "soft_margin_loss.h", "_foreach_log1p_ops.h", "slow_conv_dilated3d.h", "var_cpu_dispatch.h", "to_sparse_bsr_native.h", "upsample_bilinear2d_backward_cuda_dispatch.h", "sym_constrain_range_ops.h", "rnn_relu_cell_compositeimplicitautograd_dispatch.h", "squeeze_native.h", "lcm.h", "slow_conv_transpose3d_cpu_dispatch.h", "functional_bfloat16.h", "triu_native.h", "unbind_copy.h", "stl_bind.h", "_sparse_csr_prod.h", "meshgrid_ops.h", "upsample_nearest2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "fft_irfft_ops.h", "_choose_qparams_per_tensor_ops.h", "multiply_ops.h", "linalg_inv.h", "FunctionRef.h", "convolution_overrideable_native.h", "_foreach_tan.h", "minimum.h", "_conj_physical_ops.h", "conv3d_native.h", "nan_to_num_cuda_dispatch.h", "mkldnn_reorder_conv3d_weight.h", "ReduceOps.h", "mkldnn_max_pool2d_backward.h", "_foreach_norm_ops.h", "hardswish_backward_ops.h", "less_equal_native.h", "fft_hfft2_compositeimplicitautograd_dispatch.h", "_sparse_sum_ops.h", "abs_native.h", "less_equal.h", "relu_ops.h", "square_native.h", "qscheme_ops.h", "geometric_meta_dispatch.h", "upsample_nearest3d_cpu_dispatch.h", "tensor.h", "sum_cuda_dispatch.h", "special_logsumexp_ops.h", "combined_traceback.h", "python_engine.h", "enum_type.h", "crow_indices_copy_ops.h", "pthreadpool.h", "interpreter.h", "argwhere_ops.h", "_foreach_log10.h", "is_pinned_native.h", "LegacyVmapTransforms.h", "PixelShuffleKernel.h", "baddbmm_ops.h", "special_shifted_chebyshev_polynomial_v_ops.h", "clamp_native.h", "TensorAdvancedIndexing.h", "logsumexp.h", "conv_depthwise3d_compositeexplicitautograd_dispatch.h", "llvmMathExtras.h", "pixelshuffle.h", "miopen_depthwise_convolution_native.h", "detach_copy.h", "_cudnn_ctc_loss_native.h", "replication_pad1d.h", "empty_strided_ops.h", "upsample_trilinear3d_cpu_dispatch.h", "negative_native.h", "_neg_view_copy.h", "_index_put_impl_cuda_dispatch.h", "_native_multi_head_attention_ops.h", "rrelu_with_noise.h", "logical_not_native.h", "clamp_min_meta.h", "fbgemm_linear_fp16_weight_fp32_activation.h", "outer_ops.h", "_reshape_from_tensor.h", "bartlett_window.h", "_foreach_sub.h", "mm.h", "Unfold2d.h", "linalg_matmul_ops.h", "geqrf.h", "geometric_cpu_dispatch.h", "padding.h", "_values_native.h", "set_data_native.h", "native_group_norm_backward_native.h", "randint_like_native.h", "batch_norm_gather_stats_with_counts_compositeexplicitautograd_dispatch.h", "special_softmax.h", "cumprod_backward_ops.h", "log_sigmoid_forward_native.h", "fft_fftn_compositeimplicitautograd_dispatch.h", "_cufft_clear_plan_cache.h", "logsumexp_native.h", "_is_all_true_ops.h", "elu_native.h", "hoist_conv_packed_params.h", "exp_meta.h", "python_variable.h", "fbgemm_linear_fp16_weight.h", "linalg_svd_compositeimplicitautograd_dispatch.h", "parse_string_literal.h", "retain_grad_ops.h", "logaddexp2.h", "Dimname.h", "std.h", "zmath.h", "fused_moving_avg_obs_fake_quant.h", "special_chebyshev_polynomial_t.h", "DispatchKeyExtractor.h", "pooling.h", "_linalg_svd.h", "is_nonzero_ops.h", "trace.h", "size_native.h", "library.h", "_histogramdd_from_bin_tensors_ops.h", "max_pool3d_with_indices.h", "_neg_view_copy_ops.h", "linalg_norm_compositeimplicitautograd_dispatch.h", "rot90_ops.h", "resolve_neg.h", "vec256.h", "type_factory.h", "indices_copy_native.h", "is_set_to_ops.h", "_int_mm_native.h", "fft_fft_compositeimplicitautograd_dispatch.h", "_upsample_bilinear2d_aa_cuda_dispatch.h", "smooth_l1_loss_meta.h", "mkldnn_rnn_layer_ops.h", "special_expm1_native.h", "signbit.h", "_adaptive_avg_pool3d_backward.h", "bernoulli_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_coo_tensor_with_dims_and_tensors_compositeexplicitautograd_dispatch.h", "_thnn_differentiable_gru_cell_backward_ops.h", "_fill_mem_eff_dropout_mask_ops.h", "max_pool3d_with_indices_backward_native.h", "_sample_dirichlet_ops.h", "exponential_cpu_dispatch.h", "linalg_vecdot.h", "_use_cudnn_ctc_loss.h", "blackman_window_compositeexplicitautograd_dispatch.h", "miopen_batch_norm.h", "_test_autograd_multiple_dispatch_view_ops.h", "convolution_overrideable.h", "q_per_channel_scales_native.h", "ts_node.h", "_cast_Short_native.h", "SmallVector.h", "histogram.h", "select_backward.h", "vec256_qint.h", "addcdiv_native.h", "vec256_int.h", "TensorDataContainer.h", "linalg_cholesky.h", "reshape.h", "simple_graph_executor_impl.h", "replication_pad2d.h", "requires_grad_native.h", "pickler.h", "_foreach_lerp_ops.h", "ConvUtils.h", "_foreach_abs_ops.h", "_nested_view_from_buffer_copy_native.h", "_linalg_slogdet_meta.h", "_scaled_dot_product_flash_attention_cuda_dispatch.h", "special_erfcx_ops.h", "linalg_eig.h", "replication_pad3d_meta.h", "_lu_with_info_ops.h", "_lu_with_info_native.h", "to_sparse_bsr.h", "sparse_compressed_tensor_ops.h", "nll_loss2d_compositeimplicitautograd_dispatch.h", "slow_conv_dilated2d_native.h", "signal_handler.h", "to_dense_ops.h", "_convolution_native.h", "context.h", "argsort_native.h", "python_nn_functions.h", "mkldnn_max_pool2d_backward_ops.h", "adaptive_max_pool3d_backward_ops.h", "resize_meta_dispatch.h", "column_stack_native.h", "replication_pad3d_backward.h", "symbolic_shape_registry_util.h", "shape_inference.h", "_sparse_semi_structured_linear_ops.h", "_upsample_nearest_exact3d_compositeexplicitautogradnonfunctional_dispatch.h", "_pack_padded_sequence_backward_ops.h", "Event.h", "trie.h", "python_scalars.h", "SortStable.h", "max_unpool3d_native.h", "_empty_affine_quantized_compositeexplicitautograd_dispatch.h", "cosh_ops.h", "special_shifted_chebyshev_polynomial_u_ops.h", "_sparse_bsc_tensor_unsafe_ops.h", "batch_norm.h", "warnings.h", "_test_warn_in_autograd_ops.h", "MPSHooksInterface.h", "sym_numel.h", "imag.h", "is_distributed_ops.h", "_adaptive_avg_pool2d.h", "expm1.h", "_cufft_set_plan_cache_max_size_ops.h", "PyInterpreter.h", "_int_mm_ops.h", "expr.h", "source_range_serialization.h", "_fused_adamw_native.h", "matrix_exp_backward.h", "alias_ops.h", "adaptive_avg_pool3d_backward_native.h", "_standard_gamma_cuda_dispatch.h", "ormqr_native.h", "linalg_tensorsolve_native.h", "_index_put_impl.h", "upsampling.h", "CUDATest.h", "indices_native.h", "_foreach_exp.h", "PrivateUse1HooksInterface.h", "_to_sparse_csr_cuda_dispatch.h", "_scaled_dot_product_flash_attention_backward.h", "_dimV_ops.h", "median_native.h", "_fused_adamw.h", "resolver.h", "max_meta.h", "clamp_max_ops.h", "special_polygamma.h", "permute_ops.h", "_ctc_loss_backward_native.h", "_foreach_floor.h", "_flash_attention_forward_cuda_dispatch.h", "special_i0e_meta.h", "log_softmax.h", "randn_native.h", "upsample_nearest2d_compositeexplicitautogradnonfunctional_dispatch.h", "_foreach_acos_ops.h", "_thnn_fused_lstm_cell_ops.h", "HIPAllocatorMasqueradingAsCUDA.h", "log10_ops.h", "sym_numel_ops.h", "ccol_indices_ops.h", "jit_type_base.h", "remove_expands.h", "transpose_copy_ops.h", "EmptyTensor.h", "adam.h", "Activation.h", "isreal_ops.h", "lift_fresh_copy_ops.h", "_foreach_add.h", "index_copy_meta.h", "convolution_backward_overrideable.h", "_upsample_bicubic2d_aa_compositeexplicitautogradnonfunctional_dispatch.h", "IndexingUtils.h", "functional_base.h", "_sample_dirichlet_cuda_dispatch.h", "_unique_ops.h", "mkldnn_adaptive_avg_pool2d_ops.h", "dropout.h", "meshgrid_native.h", "fft_fft2_ops.h", "elu_backward_ops.h", "reshape_ops.h", "_foreach_exp_ops.h", "_foreach_acos.h", "fmin_native.h", "upsample_bilinear2d_backward_meta.h", "_sparse_bsr_tensor_unsafe_compositeimplicitautograd_dispatch.h", "module.h", "_scaled_dot_product_efficient_attention_native.h", "logaddexp2_meta.h", "_foreach_cos_ops.h", "stack_ops.h", "eval.h", "_nested_tensor_from_mask_left_aligned_native.h", "TypeInfo.h", "repeat.h", "view_as_real_copy.h", "col_indices_native.h", "lexer.h", "frexp.h", "tensor.h", "quantized_batch_norm_ops.h", "MathBitsFallback.h", "linalg_matmul.h", "_upsample_bilinear2d_aa_compositeexplicitautogradnonfunctional_dispatch.h", "max_pool2d_with_indices_meta.h", "range_native.h", "slice_backward.h", "unsafe_split_with_sizes_native.h", "_cummax_helper_ops.h", "prelu_ops.h", "linalg_vector_norm_cpu_dispatch.h", "prod_ops.h", "batch_norm_update_stats.h", "inplace_check.h", "prepack_folding.h", "clear_undefinedness.h", "DeviceGuardImplInterface.h", "embedding_backward.h", "silu_backward_ops.h", "slow_conv3d_native.h", "_scaled_dot_product_flash_attention_ops.h", "cudnn_convolution_add_relu_cuda_dispatch.h", "cumsum_native.h", "file_check.h", "batch_norm_backward_elemt_ops.h", "python_tracer.h", "logcumsumexp_native.h", "avg_pool2d_cuda_dispatch.h", "boxing.h", "prelu_native.h", "masked_select_backward_native.h", "_cudnn_ctc_loss_ops.h", "_upsample_nearest_exact2d_ops.h", "arcsinh_native.h", "_thnn_differentiable_lstm_cell_backward_ops.h", "finalize.h", "refine_names_ops.h", "jit_log.h", "_transformer_encoder_layer_fwd_cpu_dispatch.h", "_fake_quantize_learnable_per_channel_affine_backward_native.h", "_nested_tensor_softmax_with_shape_ops.h", "hamming_window_ops.h", "batchnorm.h", "XnnpackUtils.h", "special_xlog1py.h", "adaptive_max_pool3d_backward_meta.h", "tanh_native.h", "vander_compositeimplicitautograd_dispatch.h", "hardsigmoid_backward_meta.h", "special_xlog1py_native.h", "_cufft_get_plan_cache_max_size_native.h", "fmod_native.h", "_standard_gamma_grad_native.h", "mkldnn_rnn_layer_backward_cpu_dispatch.h", "unique_consecutive.h", "mish_native.h", "_foreach_log.h", "lift_native.h", "module.h", "_standard_gamma_compositeexplicitautograd_dispatch.h", "_log_softmax_meta.h", "_stack.h", "fft_fft_native.h", "diagonal_copy.h", "TensorUtils.h", "op_allowlist.h", "median.h", "zeros.h", "_flash_attention_forward.h", "_foreach_addcdiv_native.h", "FakeQuantAffine.h", "ravel_native.h", "add_if_then_else.h", "nll_loss2d_forward_cpu_dispatch.h", "_nnpack_available_native.h", "atan2_ops.h", "_convert_indices_from_coo_to_csr_native.h", "GPUTrace.h", "TensorFactories.h", "full_ops.h", "vsplit.h", "conv_serialization.h", "_foreach_log2.h", "bartlett_window_compositeexplicitautograd_dispatch.h", "thnn_conv2d_compositeimplicitautograd_dispatch.h", "FakeGuardImpl.h", "RegistrationHandleRAII.h", "igamma.h", "OperationUtils.h", "SymInt.h", "arcsin.h", "slice_scatter_compositeexplicitautogradnonfunctional_dispatch.h", "fft_ihfftn.h", "_mkldnn_reshape_native.h", "scaled_dot_product_attention.h", "contiguous_ops.h", "fake_quantize_per_tensor_affine_cachemask_backward_ops.h", "_fused_adam_compositeexplicitautograd_dispatch.h", "dense_dim_ops.h", "kaiser_window_native.h", "frac_native.h", "i0_native.h", "reflection_pad2d_backward_ops.h", "baddbmm_meta.h", "xlogy_meta.h", "max_pool2d_with_indices_backward.h", "TensorTopK.h", "_cufft_set_plan_cache_max_size.h", "floor_divide.h", "SparseCsrTensorUtils.h", "_to_sparse_csr.h", "empty_compositeexplicitautograd_dispatch.h", "randint_like_compositeexplicitautograd_dispatch.h", "divide_native.h", "_linalg_solve_ex_ops.h", "is_conj.h", "and_native.h", "is_neg_native.h", "fft_irfft_compositeimplicitautograd_dispatch.h", "allclose.h", "nll_loss_forward_compositeexplicitautogradnonfunctional_dispatch.h", "erfc_native.h", "bernoulli_meta_dispatch.h", "register_ops_utils.h", "_upsample_bicubic2d_aa_backward_cuda_dispatch.h", "rnn.h", "special_shifted_chebyshev_polynomial_t_ops.h", "special_gammainc_native.h", "import_source.h", "upsample_trilinear3d_meta.h", "ceil_meta.h", "slow_conv_dilated3d_native.h", "_index_put_impl_compositeexplicitautograd_dispatch.h", "cpython_defs.h", "_shape_as_tensor_native.h", "log_softmax_compositeexplicitautograd_dispatch.h", "arctanh.h", "normal_cpu_dispatch.h", "movedim.h", "cpp_prefix.h", "peephole_dict_idioms.h", "tensorpipe_agent.h", "batch_norm_elemt_cuda_dispatch.h", "_efficientzerotensor.h", "vec256_float_vsx.h", "resolve_conj_native.h", "repeat_native.h", "conv2d_native.h", "_embedding_bag_dense_backward_ops.h", "lu_unpack.h", "python_symnode.h", "Sorting.h", "tensor.h", "_foreach_tanh_ops.h", "lt_native.h", "convolution_backward_overrideable_ops.h", "group_norm.h", "Variadic.h", "fft_fft_ops.h", "MTIAHooksInterface.h", "is_neg.h", "bucketize_ops.h", "frac.h", "backend_debug_handler.h", "empty_quantized_ops.h", "sort.h", "_prelu_kernel_backward_native.h", "fill_diagonal_native.h", "multilabel_margin_loss_forward.h", "linear.h", "linalg_lu_factor.h", "_sparse_log_softmax_backward_data.h", "hinge_embedding_loss_ops.h", "_sparse_csr_sum.h", "nll_loss2d_forward_cuda_dispatch.h", "multiply_native.h", "batch_norm_gather_stats_ops.h", "error_report.h", "mkldnn_adaptive_avg_pool2d_backward.h", "_sparse_log_softmax_backward_data_native.h", "nll_loss_backward_cpu_dispatch.h", "SavedTensorHooks.h", "upsample_nearest3d_meta_dispatch.h", "special_hermite_polynomial_h.h", "fake_quantize_per_tensor_affine_cachemask_backward.h", "stride_native.h", "broadcast_tensors.h", "TypeTraits.h", "scalar_tensor_ops.h", "sparse_mask_ops.h", "hsplit_native.h", "glu_jvp.h", "_cummin_helper_ops.h", "SoftmaxKernel.h", "sparse.h", "sparse_dim_native.h", "_cudnn_rnn_compositeexplicitautograd_dispatch.h", "linalg_qr_native.h", "upsample_bicubic2d_backward_meta_dispatch.h", "adaptive_max_pool3d_native.h", "special_scaled_modified_bessel_k1_native.h", "_sparse_mm.h", "base.h", "sym_storage_offset_native.h", "_conv_depthwise2d_cuda_dispatch.h", "ivalue.h", "_nnpack_spatial_convolution.h", "all_meta.h", "movedim_ops.h", "_aminmax_native.h", "triplet_margin_loss_ops.h", "fractional_max_pool2d_backward.h", "miopen_rnn_ops.h", "python_dispatch.h", "cholesky_native.h", "upsample_trilinear3d_backward_cpu_dispatch.h", "squeeze_ops.h", "split_native.h", "renorm_ops.h", "sym_constrain_range_for_size_compositeexplicitautograd_dispatch.h", "can_cast_ops.h", "sparse_csc_tensor.h", "less_equal_ops.h", "segment_reduce_native.h", "_sparse_broadcast_to_copy_ops.h", "special_log_ndtr_meta.h", "lower_tuples.h", "choose_qparams_optimized_ops.h", "sinh_ops.h", "exp_ops.h", "miopen_convolution_native.h", "cumprod_cuda_dispatch.h", "gil.h", "_assert_async.h", "_cholesky_solve_helper_ops.h", "_nested_tensor_size_native.h", "pinverse_native.h", "SerialStackImpl.h", "all_native.h", "fft_ifftshift.h", "profiler_kineto.h", "insert_quant_dequant.h", "fill_diagonal_ops.h", "upsample_nearest3d.h", "sort_cuda_dispatch.h", "CUDAGraph.h", "normal_native.h", "triu_ops.h", "binary_cross_entropy_with_logits_compositeexplicitautograd_dispatch.h", "_unsafe_index_native.h", "slow_conv_dilated3d_compositeexplicitautograd_dispatch.h", "alias_copy.h", "_thnn_fused_lstm_cell_backward_native.h", "_scaled_dot_product_flash_attention_backward_cuda_dispatch.h", "special_gammainc.h", "rand_compositeexplicitautograd_dispatch.h", "sleef.h", "sym_constrain_range_native.h", "qr.h", "values_copy_native.h", "slice_copy_compositeexplicitautograd_dispatch.h", "_fake_quantize_learnable_per_channel_affine_native.h", "_native_multi_head_attention_compositeexplicitautograd_dispatch.h", "_test_optional_floatlist_cpu_dispatch.h", "special_bessel_j0_ops.h", "_sparse_coo_tensor_unsafe_native.h", "is_leaf_ops.h", "_native_batch_norm_legit_no_training.h", "dequantize_native.h", "row_stack.h", "_sparse_coo_tensor_with_dims_ops.h", "unfold_copy_ops.h", "_upsample_bicubic2d_aa_meta.h", "clamp_min.h", "conv_tbc_ops.h", "backend_detail.h", "function_schema.h", "std_compositeimplicitautograd_dispatch.h", "nll_loss_nd.h", "ceil_div.h", "nonzero_static_ops.h", "div_cuda_dispatch.h", "sigmoid_native.h", "_adaptive_avg_pool2d_backward_ops.h", "_foreach_lgamma.h", "erfinv_native.h", "slow_conv3d_compositeimplicitautograd_dispatch.h", "miopen_depthwise_convolution_cuda_dispatch.h", "smooth_l1_loss_backward_native.h", "replication_pad2d_backward_native.h", "glu_jvp_native.h", "wrap_outputs.h", "threshold_backward_meta.h", "add_ops.h", "PlumbingHelper.h", "adaptive_max_pool2d_backward.h", "fake_quantize_per_channel_affine_cachemask_native.h", "lcm_meta.h", "nonzero_numpy_ops.h", "dstack.h", "static.h", "tril_indices_native.h", "repeat_interleave_cpu_dispatch.h", "scaled_dot_product_attention_ops.h", "variable_factories.h", "silu_meta.h", "hash.h", "unsqueeze.h", "_sparse_mm_reduce_impl_backward.h", "native_dropout_cuda_dispatch.h", "unsafe_chunk.h", "special_legendre_polynomial_p.h", "_pad_enum_native.h", "symbolic_shape_runtime_fusion.h", "_validate_sparse_csr_tensor_args_ops.h", "CompositeExplicitAutogradFunctions_inl.h", "layer_norm_compositeimplicitautograd_dispatch.h", "diff_native.h", "_upsample_bicubic2d_aa_backward_meta_dispatch.h", "Copy.h", "Device.h", "upsample_bicubic2d_backward_cpu_dispatch.h", "bitwise_and_native.h", "init.h", "slow_conv_dilated3d_cuda_dispatch.h", "exp.h", "logaddexp2_native.h", "unpickled_python_call.h", "sort_cpu_dispatch.h", "dot_ops.h", "divide.h", "_is_zerotensor.h", "histogramdd_native.h", "special_modified_bessel_i1_ops.h", "upsample_linear1d_ops.h", "_grid_sampler_2d_cpu_fallback_backward.h", "c10d.h", "sparse_resize.h", "miopen_rnn_native.h", "_foreach_trunc_ops.h", "special_chebyshev_polynomial_u_ops.h", "cosh.h", "take_along_dim_ops.h", "insert_guards.h", "ne.h", "is_signed_ops.h", "parse_operators.h", "_foreach_sigmoid.h", "view_as_native.h", "_foreach_log2_native.h", "_int_mm.h", "_debug_has_internal_overlap.h", "tensor_types.h", "constants.h", "fft_hfft.h", "mH.h", "remove_dropout.h", "cpp_codegen.h", "randn_compositeexplicitautograd_dispatch.h", "_to_copy.h", "elu_backward_native.h", "indices.h", "special_round_native.h", "_test_autograd_multiple_dispatch_view_copy_ops.h", "batch_norm_gather_stats_cuda_dispatch.h", "_upsample_bicubic2d_aa_native.h", "_sparse_coo_tensor_unsafe.h", "cauchy_cpu_dispatch.h", "log_sigmoid_forward.h", "linalg_norm_native.h", "custom_class_detail.h", "Fill.h", "PythonTorchFunctionTLS.h", "bmm_ops.h", "ceil_native.h", "special_erfc.h", "crow_indices_copy.h", "argmin_compositeexplicitautogradnonfunctional_dispatch.h", "silu_backward_meta.h", "lstm.h", "pdist_ops.h", "_upsample_bilinear2d_aa_backward_cuda_dispatch.h", "geometric_compositeexplicitautograd_dispatch.h", "result_type_ops.h", "threshold.h", "max_pool1d_with_indices_native.h", "_spdiags_cpu_dispatch.h", "reshape_as.h", "flatbuffer_serializer_jit.h", "linalg_lu_ops.h", "SampledAddmmKernel.h", "bitwise_right_shift_meta.h", "batch_norm_backward_elemt_cuda_dispatch.h", "kron.h", "column_stack_ops.h", "Functions.h", "conv.h", "inline_autodiff_subgraphs.h", "conv2d.h", "_make_per_tensor_quantized_tensor_ops.h", "linalg_lstsq_native.h", "nll_loss2d_forward_ops.h", "resize_compositeexplicitautograd_dispatch.h", "mean_ops.h", "_sparse_coo_tensor_with_dims_and_tensors_native.h", "log_sigmoid_backward_native.h", "lower_grad_of.h", "exponential_compositeexplicitautograd_dispatch.h", "is_complex_ops.h", "zeros_ops.h", "frozen_ops_to_mkldnn.h", "max_pool2d.h", "_foreach_tan_ops.h", "permute_native.h", "_foreach_mul_native.h", "greater_equal_ops.h", "device_type_analysis.h", "linalg_tensorsolve_ops.h", "linalg_cholesky_ex_native.h", "upsample_nearest2d_backward_meta_dispatch.h", "_foreach_floor_ops.h", "logging.h", "avg_pool3d_backward_native.h", "_convolution_ops.h", "_test_serialization_subcmul.h", "backend_init.h", "_foreach_lgamma_native.h", "ATen_pch.h", "_fused_dropout_cuda_dispatch.h", "expanding_array.h", "gelu_backward_meta.h", "split_copy.h", "native_group_norm_backward_cpu_dispatch.h", "lerp_meta.h", "_sobol_engine_initialize_state.h", "normal.h", "logit_backward_meta_dispatch.h", "sparse_bsc_tensor.h", "msort_native.h", "to_mkldnn.h", "FunctionalizeInterpreter.h", "kron_native.h", "edit_distance.h", "conv_depthwise3d_cuda_dispatch.h", "adaptive_max_pool1d.h", "_nested_tensor_from_mask.h", "nll_loss2d_backward_cpu_dispatch.h", "cudnn_batch_norm_backward_cuda_dispatch.h", "PackedParams.h", "layer_norm.h", "tril_indices.h", "_nnz_ops.h", "special_log1p_ops.h", "block_diag_ops.h", "pad_ops.h", "data.h", "ArrayRef.h", "_ctc_loss_backward.h", "remainder_meta.h", "conj_ops.h", "quantized_batch_norm.h", "import.h", "avg_pool2d_backward_cpu_dispatch.h", "input-archive.h", "resize_as_sparse_native.h", "select_scatter_native.h", "memory_snapshot.h", "sigmoid.h", "sspaddmm_native.h", "full_like.h", "maximum_native.h", "python_sparse_functions.h", "tensor.h", "subtract_ops.h", "reflection_pad2d_native.h", "combinations.h", "arccosh_native.h", "Generator.h", "cos_meta.h", "log_normal_cpu_dispatch.h", "scatter_reduce.h", "div_ops.h", "arcsinh_ops.h", "cov_compositeimplicitautograd_dispatch.h", "sign_meta.h", "_foreach_erf.h", "special_bessel_j1.h", "_upsample_bilinear2d_aa_native.h", "maximum.h", "_cudnn_rnn_flatten_weight.h", "fmod_ops.h", "vec256_float_neon.h"], "new": ["_linalg_det_native.h", "_has_same_storage_numel_native.h", "erfc.h", "_sparse_mm_reduce_impl.h", "zero.h", "isposinf_ops.h", "_test_ambiguous_defaults_ops.h", "_sparse_log_softmax_ops.h", "pybind.h", "KernelFunction.h", "conj_physical_ops.h", "_scaled_dot_product_efficient_attention_backward.h", "renorm_meta.h", "roll_native.h", "take.h", "CUDAFunctions.h", "gelu_meta.h", "_convert_indices_from_csr_to_coo_ops.h", "vec512_int.h", "thnn_conv2d.h", "linalg_inv_ex_meta.h", "min.h", "log_normal_compositeexplicitautograd_dispatch.h", "_native_multi_head_attention_native.h", "_pdist_backward.h", "_copy_from_ops.h", "_foreach_erfc.h", "mean_compositeexplicitautograd_dispatch.h", "miopen_convolution_relu.h", "smm_native.h", "dsplit_ops.h", "linalg_lstsq_cpu_dispatch.h", "_nested_tensor_from_mask_left_aligned_ops.h", "binary_cross_entropy_backward.h", "_to_sparse_csr_cpu_dispatch.h", "_unsafe_index_put_ops.h", "_copy_from_native.h", "special_bessel_j1_meta.h", "unique_dim_consecutive_native.h", "minimum_native.h", "zeros_like_ops.h", "convolution_ops.h", "le.h", "cudnn_convolution_transpose_native.h", "object.h", "fake_quantize_per_tensor_affine_ops.h", "mkldnn_linear_backward_ops.h", "_adaptive_avg_pool2d_backward_native.h", "tril.h", "linalg_matrix_power_native.h", "_copy_from_and_resize_native.h", "mvlgamma_ops.h", "vdot_native.h", "special_i0e.h", "sum_to_size.h", "fill.h", "_slow_conv2d_forward_native.h", "Activation.h", "fractional_max_pool2d_backward_meta.h", "ones_like_ops.h", "_histogramdd_bin_edges_cpu_dispatch.h", "t_copy_ops.h", "_make_dual_copy_ops.h", "_native_batch_norm_legit_cuda_dispatch.h", "col_indices_copy_native.h", "binary_cross_entropy_cpu_dispatch.h", "_to_sparse_bsr_cpu_dispatch.h", "ir_simplifier.h", "logical_not.h", "onnx.h", "to_dense_backward_compositeimplicitautograd_dispatch.h", "jit_exception.h", "_masked_softmax_cuda_dispatch.h", "graph_rewrite_helper.h", "norm_meta.h", "_neg_view_native.h", "sequential.h", "embedding_bag_native.h", "scalar_tensor_native.h", "triu_indices_cpu_dispatch.h", "cudnn_affine_grid_generator_ops.h", "sparse_bsc_tensor_native.h", "gather_backward_ops.h", "function_schema_inl.h", "triangular_solve_native.h", "cumsum_meta_dispatch.h", "ParallelFuture.h", "upsample_nearest1d_meta_dispatch.h", "vec256_double.h", "DispatchStub.h", "constant_pad_nd.h", "upsample_nearest3d_backward.h", "item.h", "gru.h", "fft_ifft2_native.h", "block_diag.h", "conv_transpose3d_native.h", "_test_autograd_multiple_dispatch_ops.h", "linalg_cholesky_ex_meta.h", "or.h", "linalg_ldl_factor.h", "special_laguerre_polynomial_l_ops.h", "igamma_meta.h", "_foreach_div.h", "special_logit.h", "MPSEvent.h", "special_shifted_chebyshev_polynomial_u.h", "InlineEvent.h", "_fused_dropout.h", "_upsample_nearest_exact3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "randint_like_ops.h", "sym_constrain_range_for_size_ops.h", "argmin_ops.h", "cudnn_convolution_native.h", "adaptive_avg_pool3d.h", "triu.h", "interned_strings.h", "t_copy.h", "fft_hfft_compositeimplicitautograd_dispatch.h", "_fused_adam.h", "reduction.h", "adaptive_max_pool2d_backward_meta.h", "_new_zeros_with_same_feature_meta.h", "graph_iterator.h", "_nested_tensor_from_mask_native.h", "quantize_per_tensor_dynamic.h", "sym_stride_ops.h", "QuantizerBase.h", "mT.h", "FunctionTraits.h", "register_ops_common_utils.h", "hamming_window_compositeexplicitautograd_dispatch.h", "python_torch_functions.h", "fliplr_ops.h", "native_channel_shuffle.h", "avg_pool3d_meta_dispatch.h", "disable_torch_function.h", "gather_native.h", "VmapGeneratedPlumbing.h", "upsample_bilinear2d_backward.h", "to.h", "pass_manager.h", "_foreach_cosh.h", "log_normal_meta_dispatch.h", "sym_storage_offset.h", "DispatchKey.h", "MT19937RNGEngine.h", "conv_tbc.h", "name_mangler.h", "vander.h", "_cudnn_rnn.h", "_sparse_mask_projection_ops.h", "upsample_nearest2d_meta_dispatch.h", "_nested_select_backward_ops.h", "_prelu_kernel.h", "python_print.h", "miopen_convolution_transpose_compositeexplicitautograd_dispatch.h", "sort_meta_dispatch.h", "geometric_ops.h", "perf-inl.h", "_cast_Float_native.h", "SizesAndStrides.h", "_reshape_from_tensor_native.h", "guard_elimination.h", "kaiser_window_ops.h", "avg_pool2d_backward_meta.h", "miopen_depthwise_convolution.h", "frac_ops.h", "variadic.h", "fft.h", "mps_convolution_transpose_backward_native.h", "topk_ops.h", "_test_check_tensor_ops.h", "_masked_scale_native.h", "_log_softmax_backward_data_meta.h", "to_sparse_csc_native.h", "special_scaled_modified_bessel_k1_meta.h", "_coalesced.h", "TensorBody.h", "isfinite_ops.h", "diag_embed_ops.h", "_unsafe_view_native.h", "_to_dense_compositeexplicitautograd_dispatch.h", "addr_native.h", "tile_ops.h", "concatenate.h", "torch_dispatch_mode.h", "rrelu_with_noise_native.h", "_dim_arange.h", "lt.h", "minimum_ops.h", "sum_to_size_native.h", "index_reduce_native.h", "softplus_native.h", "diff_ops.h", "_slow_conv2d_backward_native.h", "mkldnn_reorder_conv3d_weight_compositeexplicitautograd_dispatch.h", "random_cpu_dispatch.h", "code_template.h", "where_ops.h", "to_padded_tensor_ops.h", "Copy.h", "fft_ifftn_native.h", "SegmentReduce.h", "_histogramdd_bin_edges_native.h", "atleast_1d_native.h", "fft_ihfft.h", "std_mean_cpu_dispatch.h", "view_as_real_copy_native.h", "alpha_dropout.h", "sinc.h", "cumprod_meta_dispatch.h", "shape.h", "ger_native.h", "hardtanh_backward_native.h", "glu_native.h", "python_enum_tag.h", "replication_pad1d_backward_meta.h", "gradient_native.h", "to_sparse_csr_ops.h", "logspace.h", "concat_opt.h", "_indices_copy_native.h", "type_parser.h", "_batch_norm_impl_index_backward_native.h", "_convert_indices_from_csr_to_coo.h", "ResizeCommon.h", "example.h", "igammac_native.h", "_cast_Int_native.h", "_fft_c2c.h", "_to_sparse_bsc_native.h", "rnn_tanh.h", "log_native.h", "BinaryOps.h", "linalg_norm_ops.h", "_flash_attention_backward.h", "randn_like_compositeexplicitautograd_dispatch.h", "prod_compositeimplicitautograd_dispatch.h", "_validate_sparse_bsc_tensor_args.h", "reflection_pad1d_backward_ops.h", "_dirichlet_grad_native.h", "_linalg_check_errors_ops.h", "_values_copy_ops.h", "any_native.h", "sin_ops.h", "_upsample_nearest_exact3d_backward_native.h", "CompositeImplicitAutogradNestedTensorFunctions_inl.h", "searchsorted_cpu_dispatch.h", "object_ptr.h", "linalg_pinv_compositeexplicitautograd_dispatch.h", "log_meta.h", "sparse_coo_tensor_native.h", "is_signed_native.h", "util.h", "_foreach_log10_ops.h", "lazy_graph_executor.h", "zero_native.h", "linalg_lu_meta.h", "AdaptivePooling.h", "bitwise_right_shift_native.h", "fbgemm_linear_int8_weight.h", "pow_native.h", "unique_dim_ops.h", "_foreach_clamp_max_ops.h", "_validate_compressed_sparse_indices_native.h", "adaptive.h", "_linalg_svd_cpu_dispatch.h", "sparse_resize_and_clear_native.h", "sgn_native.h", "_functional_sym_constrain_range_for_size_compositeexplicitautograd_dispatch.h", "grid_sampler_ops.h", "is_complex_native.h", "nanquantile_ops.h", "fft_hfftn.h", "_fused_adam_ops.h", "ormqr.h", "linspace.h", "_adaptive_avg_pool2d_native.h", "dsplit.h", "sym_stride.h", "prod.h", "margin_ranking_loss.h", "unique_consecutive_ops.h", "col_indices_copy.h", "grid_sampler_3d_backward_native.h", "_masked_scale_ops.h", "TransformationHelper.h", "_histogramdd_from_bin_cts_native.h", "im2col_ops.h", "slice_compositeexplicitautograd_dispatch.h", "GridSamplerUtils.h", "rnn_relu_cell.h", "_histogramdd_from_bin_cts_compositeexplicitautograd_dispatch.h", "atan2.h", "_foreach_cosh_ops.h", "aminmax_cuda_dispatch.h", "_foreach_sinh_native.h", "cdist_ops.h", "linalg_solve_native.h", "miopen_convolution_cuda_dispatch.h", "transpose_native.h", "mkldnn_max_pool2d_ops.h", "bitwise_and_ops.h", "triangular_solve.h", "Exceptions.h", "batch_norm_backward_reduce_cuda_dispatch.h", "randint_native.h", "empty_quantized_native.h", "pad.h", "isinf.h", "to_dense_backward_native.h", "_pin_memory_ops.h", "negative_ops.h", "message.h", "nll_loss2d_backward_native.h", "base.h", "slow_conv_transpose2d_cuda_dispatch.h", "_cdist_forward.h", "sinh.h", "fft_fft2_compositeimplicitautograd_dispatch.h", "_sparse_coo_tensor_with_dims_and_tensors_ops.h", "is_same_size_native.h", "mse_loss_ops.h", "to_sparse_bsc_compositeimplicitautograd_dispatch.h", "_cslt_compress_ops.h", "_lstm_mps.h", "_sobol_engine_initialize_state_native.h", "nccl.h", "index_fill.h", "_thnn_differentiable_gru_cell_backward.h", "script_resp.h", "fliplr.h", "squeeze_copy_native.h", "python_tensor.h", "fbgemm_utils.h", "nll_loss_forward_ops.h", "sparse_csc_tensor_compositeimplicitautograd_dispatch.h", "miopen_convolution_relu_cuda_dispatch.h", "_foreach_copy_ops.h", "avg_pool3d_backward_ops.h", "_cslt_sparse_mm.h", "InlineStreamGuard.h", "integer_value_refinement.h", "hash_provider.h", "vander_ops.h", "permute_copy_ops.h", "softmax.h", "_conj_physical.h", "empty_permuted.h", "gru_cell.h", "expand_as_ops.h", "hspmm_native.h", "_nested_tensor_from_tensor_list.h", "full_compositeexplicitautograd_dispatch.h", "linalg_cross_native.h", "linear_backward_native.h", "vdot_ops.h", "CompositeImplicitAutogradFunctions_inl.h", "aminmax_ops.h", "AffineQuantizer.h", "_foreach_norm_compositeexplicitautograd_dispatch.h", "sort_compositeimplicitautograd_dispatch.h", "renorm.h", "AffineQuantizerBase.h", "nll_loss2d_forward_native.h", "adaptive_max_pool1d_ops.h", "_efficientzerotensor_native.h", "_addmm_activation_ops.h", "DLConvertor.h", "pixelshuffle.h", "cudnn_convolution_relu.h", "_mps_convolution_native.h", "make_boxed_from_unboxed_functor.h", "view_as_complex_copy_native.h", "_embedding_bag_forward_only_cuda_dispatch.h", "batch_norm_stats_ops.h", "_test_autograd_multiple_dispatch_view_copy.h", "lcm_ops.h", "fft_rfft_compositeimplicitautograd_dispatch.h", "_convert_indices_from_csr_to_coo_meta.h", "index_native.h", "_foreach_ceil.h", "split_copy_ops.h", "batch_norm_ops.h", "sym_size.h", "_sobol_engine_ff_native.h", "miopen_convolution_ops.h", "cross_compositeimplicitautograd_dispatch.h", "compiled_autograd.h", "_sparse_sum_backward.h", "_sparse_csr_tensor_unsafe_native.h", "igamma_ops.h", "queue.h", "sparse_bitset.h", "_efficient_attention_forward_ops.h", "cudnn_batch_norm_cuda_dispatch.h", "_native_batch_norm_legit_no_training_ops.h", "cudnn_batch_norm_backward_native.h", "linalg_matrix_exp_native.h", "new_empty_strided_native.h", "_foreach_lerp.h", "Layout.h", "_adaptive_avg_pool3d_backward_native.h", "linalg_cond.h", "multilabel_margin_loss_native.h", "fft_hfft2_native.h", "quantize_per_tensor_dynamic_ops.h", "hardswish_ops.h", "import_export_functions.h", "clamp_min_ops.h", "to_dense_compositeimplicitautograd_dispatch.h", "lt_ops.h", "BFloat16.h", "data_native.h", "orgqr.h", "count_nonzero_compositeexplicitautograd_dispatch.h", "linalg_eig_ops.h", "Synchronized.h", "cumsum_ops.h", "le_native.h", "round_native.h", "PythonDispatcherTLS.h", "mkldnn_rnn_layer_native.h", "binary_cross_entropy_backward_cuda_dispatch.h", "index_select_ops.h", "linalg_inv_ex_ops.h", "isinf_ops.h", "vec256_float.h", "sym_constrain_range_for_size.h", "ChannelShuffleKernel.h", "miopen_rnn_compositeexplicitautograd_dispatch.h", "quantized_max_pool1d.h", "_foreach_add_native.h", "_batch_norm_impl_index_backward_ops.h", "file_adapter.h", "reflection_pad2d_backward_native.h", "dstack_native.h", "lerp.h", "special_softmax_native.h", "linalg_ldl_factor_ex_ops.h", "corrcoef.h", "_foreach_round_ops.h", "grid_sampler_2d_backward.h", "empty_like_compositeexplicitautograd_dispatch.h", "numpy_T.h", "gradient_compositeimplicitautograd_dispatch.h", "miopen_convolution_add_relu_cuda_dispatch.h", "amin_ops.h", "_neg_view.h", "concatenate_ops.h", "special_scaled_modified_bessel_k1_ops.h", "mkldnn_max_pool3d_backward.h", "clamp_max_native.h", "CUDAPluggableAllocator.h", "instance_norm_compositeimplicitautograd_dispatch.h", "_log_softmax_backward_data.h", "fbgemm_linear_int8_weight_fp32_activation.h", "_fw_primal_ops.h", "_cudnn_init_dropout_state.h", "native_dropout_ops.h", "clamp_cuda_dispatch.h", "where.h", "reflection_pad3d.h", "_segment_reduce_backward.h", "empty_compositeimplicitautograd_dispatch.h", "lu_unpack_native.h", "from_file.h", "_amp_foreach_non_finite_check_and_unscale_native.h", "_sparse_mm_reduce_impl_backward_ops.h", "sort_ops.h", "diagonal_copy_ops.h", "pixel_unshuffle.h", "bartlett_window_native.h", "lgamma_ops.h", "special_digamma_ops.h", "gradient_ops.h", "avg_pool3d_compositeexplicitautogradnonfunctional_dispatch.h", "mean_meta.h", "stack_native.h", "sort_native.h", "sym_storage_offset_ops.h", "nll_loss_forward_meta_dispatch.h", "CPUGeneratorImpl.h", "adaptive_max_pool3d_ops.h", "Tensor.h", "scatter_reduce_ops.h", "size_ops.h", "nanmedian.h", "_reshape_alias_copy_native.h", "remove_mutation.h", "view_copy.h", "narrow_copy_ops.h", "_fused_moving_avg_obs_fq_helper_native.h", "_functional_sym_constrain_range_for_size_native.h", "_to_sparse_csc_native.h", "triu_indices_native.h", "digamma_meta.h", "iterator.h", "rnn_relu_native.h", "l1_loss_ops.h", "acosh_ops.h", "row_indices_copy.h", "backend_exception.h", "_linalg_svd_native.h", "_index_put_impl_native.h", "ComplexHelper.h", "_foreach_sin_native.h", "batch_norm_backward_elemt_native.h", "hardsigmoid.h", "FractionalMaxPooling.h", "ccol_indices_native.h", "index_copy.h", "rsub.h", "_embedding_bag_backward_native.h", "cat.h", "diagonal_backward_native.h", "DeviceType.h", "inline_loop_condition.h", "driver_api.h", "triu_indices_cuda_dispatch.h", "lift_fresh_copy.h", "rref_impl.h", "_log_softmax_backward_data_ops.h", "graph_node_list.h", "ne_native.h", "cov_native.h", "XPUHooksInterface.h", "uniform_ops.h", "TopKImpl.h", "_validate_compressed_sparse_indices_ops.h", "_pad_packed_sequence_ops.h", "TracerMode.h", "replication_pad3d.h", "_mps_convolution_compositeexplicitautograd_dispatch.h", "special_expit_ops.h", "upsample_bilinear2d_backward_native.h", "_histogramdd_from_bin_cts.h", "CUDAFunctions_inl.h", "cudnn_convolution_relu_cuda_dispatch.h", "dstack_ops.h", "cumprod_compositeimplicitautograd_dispatch.h", "conv_transpose1d.h", "special_chebyshev_polynomial_w.h", "constant_pad_nd_native.h", "upsample_bicubic2d_compositeimplicitautograd_dispatch.h", "_fake_quantize_learnable_per_tensor_affine_backward_native.h", "multilabel_margin_loss.h", "LeftRight.h", "round_ops.h", "triplet_margin_loss_native.h", "polygamma_meta.h", "max_unpool3d_ops.h", "fake_quantize_per_channel_affine_cachemask_backward.h", "polygamma_native.h", "rpc_command_base.h", "resize_as_sparse_ops.h", "data_shuttle.h", "_weight_norm_interface_backward_ops.h", "clamp_compositeexplicitautogradnonfunctional_dispatch.h", "normalization.h", "python_ir.h", "observer.h", "scaled_dot_product_attention_compositeimplicitautograd_dispatch.h", "CUDACachingAllocator.h", "_upsample_nearest_exact3d_native.h", "MPSHooks.h", "mul_ops.h", "replication_pad2d_native.h", "special_erfcx_native.h", "_linalg_det_meta.h", "is_signed.h", "upsample_bicubic2d_meta.h", "choose_qparams_optimized_native.h", "sparse_resize_and_clear.h", "is_conj_ops.h", "xlogy_ops.h", "_foreach_asin_ops.h", "adaptive_avg_pool1d_native.h", "_pdist_forward_ops.h", "native_dropout_native.h", "logical_xor_ops.h", "_test_optional_filled_intlist_ops.h", "unsqueeze_native.h", "error_messages.h", "allclose_native.h", "_use_cudnn_rnn_flatten_weight_native.h", "dense_dim_native.h", "quantize_per_tensor_ops.h", "_indices_copy_ops.h", "binary_cross_entropy_backward_native.h", "avg_pool2d_meta.h", "heaviside_ops.h", "upsample_linear1d_compositeimplicitautograd_dispatch.h", "_sparse_broadcast_to_native.h", "addmm_meta.h", "reflection_pad2d_ops.h", "triu_meta.h", "repeat_interleave_compositeimplicitautograd_dispatch.h", "q_per_channel_axis_ops.h", "_cast_Double_native.h", "throughput_benchmark.h", "special_gammaln.h", "addbmm_native.h", "special_bessel_y0_meta.h", "cumprod_compositeexplicitautogradnonfunctional_dispatch.h", "fft_ifft2.h", "out_types.h", "softshrink_backward.h", "bitwise_right_shift.h", "vsplit_native.h", "conv2d_compositeimplicitautograd_dispatch.h", "mm_native.h", "glu_backward.h", "as_strided_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_to_cpu.h", "sin.h", "_mps_convolution_ops.h", "trunc_meta.h", "addmm_ops.h", "native_batch_norm_backward.h", "Types.h", "_native_multi_head_attention.h", "mkldnn_adaptive_avg_pool2d_backward_native.h", "special_legendre_polynomial_p_ops.h", "output-archive.h", "mem_dependency_checker.h", "symbolic.h", "_amp_update_scale_ops.h", "fft_rfft2_ops.h", "autograd.h", "max_unpool3d.h", "_foreach_copy_native.h", "addmv_ops.h", "_autocast_to_full_precision_ops.h", "QnnpackUtils.h", "cosine_embedding_loss_native.h", "reflection_pad1d_ops.h", "serialize.h", "scatter_add_native.h", "EmptyTensor.h", "all_ops.h", "linalg_inv_ex.h", "block_diag_native.h", "_foreach_log2_ops.h", "linalg_eigvals.h", "comm.h", "poisson_native.h", "vec512_bfloat16.h", "source_ref.h", "_pad_circular_ops.h", "rand_like_native.h", "addmm.h", "copysign_ops.h", "_unique2.h", "pickle.h", "masked_select_backward.h", "adjoint_native.h", "TensorShape.h", "huber_loss_backward.h", "TensorIteratorDynamicCasting.h", "conv_transpose1d_ops.h", "Functions.h", "div_compositeexplicitautogradnonfunctional_dispatch.h", "var_mean_compositeimplicitautograd_dispatch.h", "_upsample_nearest_exact2d_meta.h", "arctan_native.h", "mv.h", "dropout.h", "unsafe_split_with_sizes_ops.h", "linalg_det_ops.h", "new_empty_native.h", "upsample_nearest2d_backward_meta.h", "logspace_native.h", "copysign_native.h", "conv1d_compositeimplicitautograd_dispatch.h", "can_cast_compositeimplicitautograd_dispatch.h", "mps_convolution_backward_ops.h", "instance_norm_native.h", "lshift.h", "split.h", "TraceUtils.h", "quantile_ops.h", "is_vulkan_available.h", "unflatten_dense_tensors_native.h", "Load.h", "binary_cross_entropy.h", "fractional_max_pool2d_ops.h", "python_resp.h", "log_normal_ops.h", "baddbmm.h", "_reshape_from_tensor_ops.h", "native_channel_shuffle_ops.h", "copy_native.h", "special_laguerre_polynomial_l_meta.h", "_assert_async_ops.h", "RNN.h", "histogram_cpu_dispatch.h", "exp2_meta.h", "lift_ops.h", "avg_pool2d_backward_ops.h", "isin_ops.h", "unfold.h", "stack.h", "ones_like.h", "_softmax.h", "python_compat.h", "conj_physical.h", "blackman_window_ops.h", "fft_ihfft2_ops.h", "_scaled_dot_product_efficient_attention_backward_ops.h", "_foreach_erf_native.h", "canonicalize_graph_fuser_ops.h", "index_copy_ops.h", "to_mkldnn_cpu_dispatch.h", "repeat_interleave.h", "BoxedKernel_impl.h", "upsample_linear1d.h", "broadcast_tensors_native.h", "repeat_interleave_cuda_dispatch.h", "special_expit_native.h", "view_as_complex_ops.h", "linalg_ldl_factor_native.h", "reciprocal_native.h", "base.h", "FunctionOfAMatrixUtils.h", "fliplr_native.h", "_cudnn_ctc_loss.h", "ger_ops.h", "_add_relu.h", "detach_native.h", "coalesce_native.h", "atanh_native.h", "_scaled_mm_cuda_dispatch.h", "PhiloxRNGEngine.h", "batch_norm_update_stats_ops.h", "sign_ops.h", "upsample_linear1d_meta_dispatch.h", "_foobar_native.h", "_cummax_helper_native.h", "grid_sampler_2d_ops.h", "cudnn_affine_grid_generator.h", "cholesky_ops.h", "fbgemm_pack_gemm_matrix_fp16_native.h", "_foreach_asin.h", "embed.h", "linalg_tensorinv.h", "CUDABlas.h", "TensorWrapper.h", "Reduction.h", "upsample_trilinear3d_backward.h", "reflection_pad1d_backward_meta.h", "_nested_tensor_softmax_with_shape_native.h", "adjoint_ops.h", "native_layer_norm_backward_ops.h", "Resize.h", "threshold_native.h", "bitwise_xor_meta.h", "CallOnce.h", "LaunchUtils.h", "sum.h", "adaptive_max_pool3d_backward.h", "util.h", "sgn.h", "row_indices_native.h", "special_log_softmax.h", "vec256_complex_double.h", "_convolution_compositeimplicitautograd_dispatch.h", "Copy.h", "pinverse.h", "DispatchKeySet.h", "_upsample_nearest_exact1d_meta_dispatch.h", "_to_sparse_csc_compositeexplicitautograd_dispatch.h", "arccos_native.h", "negative.h", "python_sugared_value.h", "nested_to_padded_tensor.h", "argmin_native.h", "VariableTypeUtils.h", "container.h", "native_channel_shuffle_native.h", "_upsample_nearest_exact1d_backward_cuda_dispatch.h", "stack.h", "_to_sparse_cuda_dispatch.h", "_convolution_double_backward_ops.h", "Parallel-inl.h", "randperm_cuda_dispatch.h", "fft_ifftn_ops.h", "_test_ambiguous_defaults.h", "abs_ops.h", "_upsample_bicubic2d_aa_backward_cpu_dispatch.h", "padding.h", "python_call.h", "nll_loss_ops.h", "python_tree_views.h", "_sparse_csc_tensor_unsafe.h", "Histogram.h", "custom_function.h", "_sparse_broadcast_to_copy_native.h", "_foreach_ceil_native.h", "new_ones_compositeexplicitautograd_dispatch.h", "_cast_Half_native.h", "upsample_nearest3d_backward_ops.h", "isreal_native.h", "_batch_norm_impl_index_compositeimplicitautograd_dispatch.h", "conv_transpose2d_native.h", "stft.h", "FuncTorchTLS.h", "replication_pad1d_ops.h", "special_round_ops.h", "lerp_native.h", "ExclusivelyOwned.h", "_foreach_sigmoid_ops.h", "_fill_mem_eff_dropout_mask_native.h", "_linalg_check_errors.h", "special_scaled_modified_bessel_k0_ops.h", "_sparse_softmax_backward_data_ops.h", "randperm_ops.h", "_amp_foreach_non_finite_check_and_unscale.h", "lstm_cell.h", "linalg_matrix_norm_native.h", "_nested_view_from_buffer_ops.h", "_histogramdd_from_bin_tensors.h", "_sparse_mm_reduce_impl_native.h", "jit_decomp_interface.h", "remainder_ops.h", "matmul_backward_native.h", "_to_dense.h", "conv2d_ops.h", "stateful.h", "_euclidean_dist.h", "_mps_convolution.h", "python_nested_functions.h", "group_norm.h", "tensor_layouts.h", "_cudnn_rnn_backward_native.h", "profiling_graph_executor_impl.h", "embedding_renorm.h", "resolve_conj_ops.h", "_fft_c2r_native.h", "conv_tbc_backward_ops.h", "_cdist_backward_ops.h", "request_callback.h", "special_spherical_bessel_j0_ops.h", "mse_loss_backward_native.h", "resize_native.h", "histogramdd_ops.h", "_backward_compositeimplicitautograd_dispatch.h", "upsample_nearest2d_backward_native.h", "index_add.h", "_foreach_neg_ops.h", "_nnz_native.h", "floor_native.h", "linspace_native.h", "_resize_output_native.h", "square.h", "softplus_meta.h", "_nested_from_padded_and_nested_example_ops.h", "view_as_complex_copy_ops.h", "strides.h", "set.h", "cuda.h", "linalg_diagonal.h", "linalg_ldl_solve_ops.h", "adaptive_avg_pool2d_ops.h", "select.h", "special_shifted_chebyshev_polynomial_u_native.h", "nll_loss_forward.h", "types.h", "copysign.h", "relu.h", "slow_conv3d_ops.h", "q_per_channel_scales.h", "special_legendre_polynomial_p_meta.h", "value_selecting_reduction_backward_ops.h", "_test_optional_intlist.h", "parser.h", "cholesky_inverse.h", "slice_copy_ops.h", "lr_scheduler.h", "_choose_qparams_per_tensor.h", "linalg_ldl_factor_ex_meta.h", "DeviceThreadHandles.h", "lstm_native.h", "exception.h", "conv_tbc_native.h", "slow_conv_transpose2d.h", "cummax_native.h", "quantized_rnn_tanh_cell_ops.h", "diag_embed.h", "t.h", "group_norm_native.h", "mse_loss_backward.h", "_local_scalar_dense_native.h", "cholesky_solve_native.h", "_linalg_eigh_native.h", "RedispatchFunctions.h", "affine_grid_generator.h", "unbind.h", "FunctionalStorageImpl.h", "thread_pool.h", "chalf.h", "mkldnn_rnn_layer_backward.h", "scalar_tensor.h", "logit.h", "LinearAlgebra.h", "view.h", "exception_message.h", "max_pool2d_backward_ops.h", "avg_pool1d.h", "vec512_float.h", "clone_ops.h", "as_strided_scatter.h", "diagflat_native.h", "embedding.h", "diag.h", "named_any.h", "StackKernel.h", "batch_norm_native.h", "_embedding_bag_cuda_dispatch.h", "index_select_native.h", "upsample_trilinear3d_cuda_dispatch.h", "_fill_mem_eff_dropout_mask.h", "gelu_backward.h", "as_strided_meta_dispatch.h", "_sparse_coo_tensor_with_dims_native.h", "binomial.h", "resize.h", "empty_cuda_dispatch.h", "RuyUtils.h", "soft_margin_loss_backward_ops.h", "pixel_unshuffle_ops.h", "avg_pool3d_backward_cpu_dispatch.h", "symbolic_shape_analysis.h", "ldexp_ops.h", "utf8_decoding_ignore.h", "reshape_as_ops.h", "triangular_solve_meta.h", "dense_dim.h", "types.h", "chalf_compositeimplicitautograd_dispatch.h", "to_mkldnn_ops.h", "cleanup_autograd_context_req.h", "upsample_bilinear2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_upsample_nearest_exact2d_native.h", "linalg_vector_norm_meta_dispatch.h", "avg_pool3d_cpu_dispatch.h", "dot_native.h", "cross_ops.h", "fbgemm_linear_quantize_weight_ops.h", "IndexKernel.h", "nansum_native.h", "fft_ifft.h", "_upsample_nearest_exact2d.h", "adaptive_avg_pool3d_native.h", "log_softmax_native.h", "linalg_ldl_factor_ex.h", "_foreach_floor_native.h", "bounds_overlap.h", "MatrixRef.h", "_indices_copy.h", "amax_ops.h", "tensordot_native.h", "svd_native.h", "div_cpu_dispatch.h", "nanmean_ops.h", "upsample_bicubic2d_backward_native.h", "q_scale.h", "rrelu_compositeimplicitautograd_dispatch.h", "sparse_csr_tensor_ops.h", "upsample_nearest3d_backward_cpu_dispatch.h", "create_functional_graphs.h", "nextafter_ops.h", "conv_transpose3d_compositeimplicitautograd_dispatch.h", "diagonal_scatter_native.h", "_upsample_bilinear2d_aa_backward_native.h", "index_copy_native.h", "logical_or.h", "utils.h", "special_zeta_ops.h", "cudnn_is_acceptable.h", "align_to_native.h", "_standard_gamma_cpu_dispatch.h", "nll_loss_compositeimplicitautograd_dispatch.h", "miopen_convolution_transpose_native.h", "logsumexp_ops.h", "linalg_pinv_compositeexplicitautogradnonfunctional_dispatch.h", "quantized_max_pool1d_native.h", "fold.h", "mH_ops.h", "log2.h", "events.h", "miopen_convolution_relu_native.h", "align_as.h", "linear_backward_ops.h", "_nested_tensor_strides_ops.h", "special_i0_ops.h", "erfc_meta.h", "scope.h", "special_chebyshev_polynomial_t_native.h", "fft_hfft2.h", "peephole_list_idioms.h", "upsample_bicubic2d_compositeexplicitautogradnonfunctional_dispatch.h", "from_file_ops.h", "_upsample_nearest_exact1d_backward_meta_dispatch.h", "matmul_backward_ops.h", "full.h", "_to_sparse_bsc.h", "randint_like.h", "miopen_convolution_add_relu.h", "deg2rad.h", "_lu_with_info.h", "native_group_norm_backward.h", "feature_dropout_native.h", "_test_functorch_fallback_ops.h", "fft_irfft2_compositeimplicitautograd_dispatch.h", "silu_ops.h", "sqrt_meta.h", "trapz.h", "absolute_native.h", "import.h", "select_copy_ops.h", "angle.h", "upsample_linear1d_compositeexplicitautogradnonfunctional_dispatch.h", "_local_scalar_dense.h", "batch_norm_update_stats_cpu_dispatch.h", "fft_fftshift.h", "_conv_depthwise2d_ops.h", "argmin_cpu_dispatch.h", "linalg_det.h", "KernelUtils.h", "cholesky_solve.h", "t_copy_native.h", "diagonal_backward_ops.h", "batch_norm_gather_stats_compositeexplicitautograd_dispatch.h", "batch_norm_elemt.h", "ADInterpreters.h", "IndexKernels.h", "mT_native.h", "linear.h", "random.h", "_histogramdd_from_bin_tensors_cpu_dispatch.h", "permute_copy_native.h", "linear.h", "Exception.h", "LazyNVRTC.h", "_cummin_helper_native.h", "special_modified_bessel_k1_meta.h", "reduction.h", "var_mean_cpu_dispatch.h", "norm_native.h", "interned_strings_class.h", "upsample_linear1d_meta.h", "C++17.h", "logit_ops.h", "loss.h", "_rowwise_prune_ops.h", "miopen_batch_norm_native.h", "frozen_linear_transpose.h", "linspace_compositeexplicitautograd_dispatch.h", "channel_shuffle.h", "convolution_backward_overrideable_native.h", "CPUFunctions_inl.h", "logit_backward_meta.h", "special_chebyshev_polynomial_v_ops.h", "amin_meta.h", "_foreach_addcdiv_ops.h", "lshift_native.h", "empty_strided_cuda_dispatch.h", "embedding_backward_native.h", "fold.h", "attributes.h", "IndexKernel.h", "_sparse_bsc_tensor_unsafe_compositeimplicitautograd_dispatch.h", "lstm_cell_compositeimplicitautograd_dispatch.h", "sequential.h", "max_pool3d_with_indices_backward_ops.h", "WrapDimUtilsMulti.h", "affine_grid_generator_ops.h", "_masked_softmax_cpu_dispatch.h", "sparse_compressed_tensor_native.h", "variable.h", "smm.h", "SpectralOpsUtils.h", "fft_rfftfreq.h", "_foreach_atan_ops.h", "CPUFixedAllocator.h", "dlpack.h", "geometric.h", "index_put_ops.h", "is_vulkan_available_ops.h", "im2col.h", "_upsample_nearest_exact1d_native.h", "embedding_ops.h", "MPSGeneratorImpl.h", "_sparse_addmm.h", "_convert_indices_from_coo_to_csr.h", "matrix_power.h", "_embedding_bag_forward_only_ops.h", "slice_scatter_compositeexplicitautograd_dispatch.h", "div_meta.h", "_log_softmax.h", "_cast_Long.h", "upsample_nearest1d_cpu_dispatch.h", "cauchy_ops.h", "alias_copy_ops.h", "to_sparse_bsc_ops.h", "linalg_cholesky_native.h", "special_bessel_j0.h", "special_entr_ops.h", "pad_sequence_compositeimplicitautograd_dispatch.h", "linalg_eigvalsh_native.h", "binomial_cuda_dispatch.h", "_grid_sampler_2d_cpu_fallback_backward_native.h", "new_ones_ops.h", "resize_cuda_dispatch.h", "round_meta.h", "reciprocal_ops.h", "nested.h", "_mkldnn_reshape_ops.h", "hinge_embedding_loss.h", "tile_native.h", "norm_compositeimplicitautograd_dispatch.h", "cudnn_batch_norm_backward_compositeexplicitautograd_dispatch.h", "_triton_multi_head_attention_cuda_dispatch.h", "instancenorm.h", "Float8_e5m2-inl.h", "conv1d_native.h", "hspmm.h", "_prelu_kernel_backward_ops.h", "_upsample_nearest_exact3d_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_w.h", "nll_loss_nd_compositeimplicitautograd_dispatch.h", "ceil_ops.h", "_sparse_semi_structured_linear.h", "TensorOptions.h", "_embedding_bag_dense_backward_cpu_dispatch.h", "_foobar.h", "quantile_compositeimplicitautograd_dispatch.h", "CUDAGuardImpl.h", "_saturate_weight_to_fp16.h", "linalg_matrix_norm_ops.h", "_native_batch_norm_legit_no_training_compositeexplicitautograd_dispatch.h", "special_modified_bessel_i0_meta.h", "parser_constants.h", "_cast_Int_ops.h", "itt_wrapper.h", "pixel_shuffle_ops.h", "common_subexpression_elimination.h", "DistributionsHelper.h", "_native_batch_norm_legit_cpu_dispatch.h", "base.h", "_scaled_dot_product_efficient_attention_ops.h", "norm_compositeexplicitautograd_dispatch.h", "einsum_ops.h", "chalf_ops.h", "fused_moving_avg_obs_fake_quant_ops.h", "OperatorEntry.h", "expand_as.h", "IndexKernel.h", "activation.h", "clip_grad.h", "Parallel.h", "affine_grid_generator_backward.h", "debug_util.h", "hamming_window_native.h", "embedding_renorm_ops.h", "CUDAEvent.h", "_foreach_tanh.h", "cumsum_compositeimplicitautograd_dispatch.h", "ravel.h", "PeerToPeerAccess.h", "embedding_sparse_backward_ops.h", "_sparse_mask_projection.h", "poisson.h", "upsample_linear1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_unique.h", "silu_native.h", "bitwise_xor_native.h", "cat_meta.h", "_sobol_engine_initialize_state_ops.h", "fractional_max_pool3d.h", "_dirichlet_grad.h", "logaddexp_native.h", "item_native.h", "_test_optional_filled_intlist_native.h", "_sparse_csr_tensor_unsafe_compositeimplicitautograd_dispatch.h", "smm_ops.h", "as_strided_ops.h", "slow_conv_dilated2d_cpu_dispatch.h", "_embedding_bag_per_sample_weights_backward_ops.h", "isneginf.h", "_fake_quantize_learnable_per_channel_affine.h", "ScalarOps.h", "buffer_info.h", "fft_ifftshift_ops.h", "searchsorted_native.h", "mode.h", "polygamma.h", "batch_norm_elemt_native.h", "_add_relu_native.h", "symbolic_shape_registry.h", "_transform_bias_rescale_qkv_native.h", "ir_metadata.h", "special_bessel_y1.h", "fusion_passes.h", "quantized_max_pool2d_native.h", "_embedding_bag_forward_only_native.h", "log_sigmoid_backward_ops.h", "flipud_ops.h", "VmapInterpreter.h", "fft_fftn.h", "_scaled_dot_product_attention_math_native.h", "fbgemm_pack_quantized_matrix_ops.h", "argmax.h", "add_native.h", "quantize_per_tensor_dynamic_native.h", "logit_meta_dispatch.h", "vec256_complex_double_vsx.h", "_sobol_engine_scramble.h", "norm_meta_dispatch.h", "_test_functorch_fallback.h", "convolution_native.h", "saved_variable_hooks.h", "var_mean_ops.h", "segment_reduce.h", "quantized_batch_norm_native.h", "Stream.h", "stream.h", "transpose_copy_native.h", "_foreach_expm1.h", "linalg_lu_factor_ex_ops.h", "is_leaf.h", "swapdims.h", "grad_mode.h", "sparse_coo_tensor_compositeexplicitautograd_dispatch.h", "asinh_native.h", "threshold_backward.h", "cosine_embedding_loss.h", "unsafe_chunk_native.h", "quantized_lstm_cell_native.h", "ts_lowering_context.h", "_masked_softmax_compositeexplicitautograd_dispatch.h", "poisson_nll_loss.h", "backend_debug_info.h", "copy_sparse_to_sparse_native.h", "slow_conv_transpose2d_meta.h", "pinverse_ops.h", "_nnpack_available_ops.h", "_saturate_weight_to_fp16_ops.h", "squeeze_copy.h", "_coalesced_ops.h", "to_compositeimplicitautograd_dispatch.h", "_foreach_log_native.h", "fft_ihfft2_native.h", "Logging.h", "_sparse_bsr_tensor_unsafe_ops.h", "comm.h", "special_i0_native.h", "lstm_ops.h", "leaky_relu_backward_native.h", "asinh.h", "fft_rfft.h", "sparse_coo_tensor.h", "builtin_function.h", "multi_margin_loss_cpu_dispatch.h", "int_repr_native.h", "Descriptors.h", "BoxedKernel.h", "arctan_ops.h", "rrelu_native.h", "zeros_like.h", "exponential_cuda_dispatch.h", "_is_zerotensor_native.h", "logit_backward_native.h", "utils.h", "signbit_ops.h", "nonzero.h", "distance.h", "matrix_exp_ops.h", "argument_spec.h", "signbit_native.h", "mean_meta_dispatch.h", "is_vulkan_available_native.h", "_to_sparse_bsr.h", "split_with_sizes_ops.h", "fix.h", "fft_irfftn_native.h", "_upsample_nearest_exact2d_cpu_dispatch.h", "positive_native.h", "segment_reduce_compositeexplicitautograd_dispatch.h", "q_per_channel_axis.h", "randn_compositeimplicitautograd_dispatch.h", "ir_dump_util.h", "_unsafe_index_put_compositeexplicitautograd_dispatch.h", "cudnn_convolution_add_relu_ops.h", "Lerp.h", "_foreach_asin_native.h", "igamma_native.h", "is_same_size.h", "_scaled_dot_product_attention_math_ops.h", "cross_native.h", "_pad_packed_sequence_native.h", "digamma.h", "digamma_native.h", "binary_cross_entropy_with_logits.h", "_to_sparse_semi_structured.h", "metal_rewrite.h", "masked_fill.h", "rnn_relu.h", "NativeFunctions.h", "_trilinear_native.h", "linalg_lstsq_cuda_dispatch.h", "_nnpack_spatial_convolution_ops.h", "_stack_ops.h", "mkldnn_max_pool2d.h", "_cslt_compress.h", "rename_native.h", "linalg_solve.h", "fractional_max_pool3d_backward_native.h", "_linalg_svd_ops.h", "special_i1e_native.h", "sum_meta_dispatch.h", "max_pool2d_native.h", "rref_backward_resp.h", "polar_native.h", "reciprocal.h", "celu.h", "trapezoid_native.h", "ceil.h", "conj.h", "TypeSafeSignMath.h", "_to_sparse_bsc_compositeexplicitautograd_dispatch.h", "constant_propagation.h", "upsample_nearest2d_ops.h", "_foreach_maximum_ops.h", "_flash_attention_backward_ops.h", "acosh.h", "quantization.h", "dropout_native.h", "cudnn_batch_norm_compositeexplicitautograd_dispatch.h", "python_saved_variable_hooks.h", "_softmax_meta.h", "stride_ops.h", "ScatterGatherChecks.h", "special_modified_bessel_k0_ops.h", "upsample_nearest2d_backward_cpu_dispatch.h", "_to_sparse_bsr_compositeexplicitautograd_dispatch.h", "glu_jvp_ops.h", "trunc_native.h", "quantization.h", "_fake_quantize_learnable_per_tensor_affine_backward.h", "gradient.h", "hardsigmoid_backward.h", "softshrink.h", "rsqrt_meta.h", "special_modified_bessel_k0.h", "BatchLinearAlgebra.h", "_foobar_ops.h", "_histogramdd_from_bin_tensors_compositeexplicitautograd_dispatch.h", "logging_is_not_google_glog.h", "_sparse_log_softmax.h", "profiler_legacy.h", "_sparse_addmm_native.h", "_sparse_broadcast_to.h", "adagrad.h", "linalg_tensorinv_ops.h", "log1p_ops.h", "diagonal_backward.h", "function_schema_parser.h", "pixel_shuffle_native.h", "rename_ops.h", "argmin_meta.h", "fake_quantize_per_channel_affine_cachemask.h", "linalg_eigvals_native.h", "quantized_rnn_tanh_cell_native.h", "decomposition_registry_util.h", "nll_loss_forward_native.h", "perf.h", "cov_ops.h", "bartlett_window_ops.h", "builtin_functions.h", "logaddexp.h", "_nested_from_padded_ops.h", "leaky_relu_meta.h", "addcdiv_meta.h", "new_empty_strided_ops.h", "custom_batch_request.h", "mkldnn_rewrite.h", "SparseTensorImpl.h", "chunk_ops.h", "new_empty.h", "upsample_trilinear3d_compositeimplicitautograd_dispatch.h", "sum_compositeexplicitautograd_dispatch.h", "linalg_eigvals_ops.h", "log_sigmoid_forward_ops.h", "cudnn_convolution_relu_compositeexplicitautograd_dispatch.h", "TensorConversions.h", "interface.h", "scalar_tensor_compositeexplicitautograd_dispatch.h", "atan_ops.h", "linalg_ldl_factor_ops.h", "test_helpers.h", "sspaddmm.h", "avg_pool3d_ops.h", "cummaxmin_backward_ops.h", "values_copy_ops.h", "permutation_util.h", "instancenorm.h", "_upsample_nearest_exact3d_backward_meta_dispatch.h", "_flash_attention_forward_ops.h", "special_i1e_meta.h", "_sparse_broadcast_to_ops.h", "one_hot_native.h", "cummax_ops.h", "special_modified_bessel_k0_meta.h", "interpreter.h", "quantized_batch_norm_compositeexplicitautograd_dispatch.h", "randint_compositeexplicitautograd_dispatch.h", "_test_autograd_multiple_dispatch_native.h", "_convert_indices_from_coo_to_csr_meta.h", "concat.h", "unbind_native.h", "mean_cuda_dispatch.h", "rand_compositeimplicitautograd_dispatch.h", "_foreach_tanh_native.h", "upsample_bicubic2d.h", "arccos.h", "adaptive_max_pool2d_ops.h", "special_ndtr_native.h", "upsample_bicubic2d_meta_dispatch.h", "binary_cross_entropy_native.h", "avg_pool1d_ops.h", "argmax_cuda_dispatch.h", "sparse_bsr_tensor_compositeimplicitautograd_dispatch.h", "_make_per_channel_quantized_tensor.h", "arange_native.h", "_fused_sdp_choice_native.h", "margin_ranking_loss_ops.h", "_upsample_bilinear2d_aa_meta_dispatch.h", "_cast_Int.h", "miopen_convolution_relu_ops.h", "linalg_lstsq_ops.h", "linalg_vector_norm_ops.h", "autograd_not_implemented_fallback.h", "fft_fftshift_ops.h", "empty_cpu_dispatch.h", "_fused_sdp_choice_ops.h", "_convolution_double_backward_compositeimplicitautograd_dispatch.h", "dequantize_ops.h", "_make_per_channel_quantized_tensor_ops.h", "linalg_lstsq_compositeexplicitautograd_dispatch.h", "erfinv_ops.h", "linalg_cond_native.h", "broadcast_to.h", "InferSize.h", "nanmedian_ops.h", "mnist.h", "max_pool3d_with_indices_ops.h", "special_airy_ai.h", "VariableHooksInterface.h", "CUDASparse.h", "combinations_ops.h", "_upsample_nearest_exact3d_compositeimplicitautograd_dispatch.h", "_weight_norm_ops.h", "_cast_Float.h", "TensorAccessor.h", "_scaled_dot_product_flash_attention_backward_native.h", "as_strided_compositeexplicitautogradnonfunctional_dispatch.h", "fbgemm_linear_int8_weight_fp32_activation_ops.h", "linalg_solve_triangular.h", "addmm_native.h", "_foreach_pow.h", "LossMulti.h", "_embedding_bag_sparse_backward_ops.h", "_nested_from_padded.h", "_cast_Char.h", "common.h", "l1_loss_native.h", "_nested_tensor_from_tensor_list_native.h", "slow_conv_transpose2d_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_log_softmax_native.h", "mish_backward.h", "linalg_vecdot_native.h", "linalg_lu_factor_ex_meta.h", "var_mean_native.h", "python_raii.h", "quantized_rnn_tanh_cell.h", "convolution.h", "quantized_gru_cell.h", "elu_backward_meta.h", "_foreach_mul.h", "istft_compositeimplicitautograd_dispatch.h", "max_native.h", "bmm_native.h", "chain_matmul_native.h", "special_modified_bessel_k1_ops.h", "ir_verifier.h", "unsafe_split_ops.h", "linalg_vector_norm_compositeexplicitautogradnonfunctional_dispatch.h", "api.h", "_fused_dropout_compositeexplicitautograd_dispatch.h", "remove_exceptions.h", "fill_native.h", "special_i1_native.h", "less.h", "_foreach_pow_ops.h", "_foreach_atan.h", "_fake_quantize_learnable_per_channel_affine_backward.h", "any.h", "_slow_conv2d_forward.h", "randint_ops.h", "saved_variable.h", "special_softmax_compositeimplicitautograd_dispatch.h", "cuda_enabled.h", "_indices_native.h", "linalg_pinv_ops.h", "_native_batch_norm_legit_compositeexplicitautograd_dispatch.h", "randn_ops.h", "_fw_primal_copy_ops.h", "Float8_e4m3fn.h", "_dimV.h", "_cudnn_init_dropout_state_cuda_dispatch.h", "scatter_add.h", "exp2.h", "smooth_l1_loss_backward.h", "Copy.h", "Reduce.h", "Distance.h", "neg.h", "upsample_nearest3d_ops.h", "isfinite.h", "_flash_attention_backward_native.h", "dataloader.h", "unfold_backward.h", "norm_compositeexplicitautogradnonfunctional_dispatch.h", "arccosh_ops.h", "Factory.h", "upsample_nearest1d.h", "_test_autograd_multiple_dispatch_view_native.h", "function_hook.h", "swapaxes_native.h", "native_dropout_backward.h", "_sparse_softmax.h", "log10_meta.h", "slow_conv_dilated2d_cuda_dispatch.h", "sparse_sampled_addmm_ops.h", "backend_device.h", "diagonal_scatter_ops.h", "is_distributed.h", "miopen_rnn_backward_compositeexplicitautograd_dispatch.h", "Device.h", "pybind.h", "_log_softmax_backward_data_native.h", "_embedding_bag_sparse_backward_compositeimplicitautograd_dispatch.h", "q_zero_point_native.h", "neg_ops.h", "_batch_norm_impl_index.h", "config.h", "Optional.h", "gelu.h", "_fw_primal.h", "helpers.h", "bilinear_ops.h", "_cudnn_init_dropout_state_ops.h", "analysis.h", "tan.h", "distance.h", "moveaxis_ops.h", "native_group_norm_compositeexplicitautograd_dispatch.h", "infinitely_differentiable_gelu_backward_ops.h", "fbgemm_linear_fp16_weight_native.h", "floor_divide_ops.h", "slow_conv_transpose3d_cuda_dispatch.h", "argmin_cuda_dispatch.h", "Repeat.h", "scatter_reduce_native.h", "split_ops.h", "_linalg_slogdet.h", "slow_conv_transpose2d_ops.h", "TensorTransformations.h", "upsample_nearest3d_backward_meta_dispatch.h", "svd.h", "isreal.h", "GridSamplerKernel.h", "einsum_compositeimplicitautograd_dispatch.h", "atleast_3d_native.h", "logging.h", "cudnn_grid_sampler.h", "byte_order.h", "repeat_ops.h", "ones_like_native.h", "narrow_copy_native.h", "unfold_backward_native.h", "registerizer.h", "_sparse_csr_prod_compositeexplicitautograd_dispatch.h", "fix_ops.h", "_convolution_mode_native.h", "sparse_csr_tensor_compositeimplicitautograd_dispatch.h", "_test_string_default_ops.h", "randn_like_ops.h", "code.h", "_prelu_kernel_ops.h", "_sparse_csr_sum_compositeexplicitautograd_dispatch.h", "requires_grad.h", "narrow.h", "_validate_sparse_csc_tensor_args_ops.h", "_batch_norm_impl_index_native.h", "addcmul_ops.h", "_foreach_log1p.h", "upsample_trilinear3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "python_autograd.h", "kthvalue.h", "QEngine.h", "transformer.h", "_make_per_tensor_quantized_tensor_native.h", "mean_compositeimplicitautograd_dispatch.h", "_conj.h", "sgd.h", "normal_compositeexplicitautograd_dispatch.h", "Scalar.h", "_use_cudnn_rnn_flatten_weight_ops.h", "slow_conv_transpose3d_native.h", "unbind_copy_native.h", "log10_native.h", "expand_copy.h", "fmod_meta.h", "_test_string_default.h", "fake_quantize_per_channel_affine_cachemask_backward_native.h", "_test_string_default_native.h", "remainder.h", "real_native.h", "script_profile.h", "tempfile.h", "python_remote_call.h", "sub.h", "any_ops.h", "fill_diagonal.h", "_foreach_mul_ops.h", "TensorBase.h", "_rowwise_prune_native.h", "_flash_attention_backward_cuda_dispatch.h", "multinomial_ops.h", "schema_info.h", "is_set_to_native.h", "TypeCast.h", "nan_to_num_native.h", "isfinite_native.h", "tril_meta.h", "linalg_matrix_rank_compositeimplicitautograd_dispatch.h", "sparse_dim.h", "parameterlist.h", "liveness.h", "trapz_ops.h", "quantized_gru_cell_native.h", "embedding_dense_backward_ops.h", "logical_or_ops.h", "linalg_vander_ops.h", "cudnn_convolution_relu_native.h", "alias_native.h", "upsample_trilinear3d_native.h", "from_file_compositeexplicitautograd_dispatch.h", "empty_meta_dispatch.h", "DeadlockDetection.h", "log_normal.h", "record_stream_ops.h", "std_ops.h", "is_inference.h", "throughput_benchmark-inl.h", "not_equal_native.h", "segment_reduce_ops.h", "softshrink_meta.h", "erf_native.h", "adaptive.h", "_embedding_bag_sparse_backward_native.h", "_masked_softmax_backward_cuda_dispatch.h", "chunk_native.h", "_cast_Half.h", "BatchedTensorImpl.h", "new_ones.h", "fft_rfft2_native.h", "view_copy_ops.h", "is_floating_point.h", "nanmean_compositeimplicitautograd_dispatch.h", "flatten.h", "_sparse_coo_tensor_unsafe_compositeimplicitautograd_dispatch.h", "_assert_tensor_metadata_ops.h", "empty_like_ops.h", "eq_native.h", "_foreach_log1p_native.h", "quantize_per_channel_ops.h", "loss.h", "tensor_new.h", "linalg_det_native.h", "rsqrt_native.h", "sigmoid_ops.h", "hspmm_ops.h", "rand.h", "ReduceUtils.h", "init.h", "not_equal_ops.h", "init.h", "diagonal_ops.h", "zero_ops.h", "miopen_batch_norm_backward.h", "to_padded_tensor_compositeexplicitautograd_dispatch.h", "inner.h", "_fused_moving_avg_obs_fq_helper.h", "split_with_sizes_copy.h", "matrix_H_ops.h", "Config.h", "_upsample_bicubic2d_aa_backward_meta.h", "_thnn_fused_gru_cell_backward.h", "cauchy_native.h", "movedim_native.h", "result_type.h", "containers.h", "CUDAGeneratorImpl.h", "matrix.h", "cub.h", "_test_optional_floatlist_ops.h", "softplus.h", "linalg_ldl_solve_native.h", "heaviside_native.h", "ts_backend_impl.h", "_to_sparse_csc_ops.h", "bitwise_xor_ops.h", "_foreach_cosh_native.h", "rename_compositeimplicitautograd_dispatch.h", "special_modified_bessel_k0_native.h", "HermeticPyObjectTLS.h", "linalg_lu_solve_meta.h", "_cudnn_rnn_flatten_weight_ops.h", "rsub_ops.h", "cudnn_affine_grid_generator_backward_native.h", "_make_per_tensor_quantized_tensor.h", "basic_ops.h", "slice.h", "py_rref.h", "ones_ops.h", "bincount_compositeexplicitautograd_dispatch.h", "cpuinfo.h", "_autocast_to_reduced_precision.h", "prod_compositeexplicitautogradnonfunctional_dispatch.h", "contiguous_native.h", "config.h", "norm_except_dim_ops.h", "upsample_bicubic2d_backward_meta.h", "scatter_meta.h", "avg_pool2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "tensorexpr_init.h", "native_dropout_backward_ops.h", "_upsample_nearest_exact2d_compositeimplicitautograd_dispatch.h", "index_cpu_dispatch.h", "diag_embed_native.h", "embedding.h", "and.h", "special_xlogy_ops.h", "sub_native.h", "WrapFunctionIntoFunctor.h", "upsampling.h", "_use_cudnn_ctc_loss_native.h", "mm_ops.h", "floor_ops.h", "any_meta.h", "log2_native.h", "cummin_ops.h", "CPUBlas.h", "chunk.h", "zeros_like_native.h", "_dimI_ops.h", "_standard_gamma_ops.h", "sin_meta.h", "Module.h", "random_native.h", "argmin.h", "_cummin_helper.h", "_foreach_div_ops.h", "all.h", "_efficientzerotensor_cuda_dispatch.h", "_is_any_true.h", "reflection_pad3d_native.h", "linalg_eigvals_compositeimplicitautograd_dispatch.h", "_sparse_mask_projection_native.h", "matrix_exp_backward_ops.h", "quantization_type.h", "_use_cudnn_rnn_flatten_weight.h", "special_spherical_bessel_j0.h", "log_sigmoid_native.h", "index_add_meta.h", "_addmm_activation_native.h", "trace_backward_native.h", "_thnn_fused_lstm_cell_backward_impl_compositeexplicitautograd_dispatch.h", "complex_ops.h", "CppSignature.h", "conv_tbc_backward.h", "LegacyVmapMode.h", "slow_conv3d_forward_native.h", "linalg_cross_meta.h", "ormqr_ops.h", "CUDADeviceAssertion.h", "_cast_Long_native.h", "elu_meta.h", "native_layer_norm_backward.h", "fft_ihfft_ops.h", "native_batch_norm_cuda_dispatch.h", "ts_autograd_functions.h", "gcd_native.h", "_conj_ops.h", "source_range.h", "col_indices_copy_ops.h", "_assert_tensor_metadata_native.h", "_autocast_to_full_precision_native.h", "_foreach_frac.h", "miopen_rnn_backward.h", "resource_guard.h", "rpc_agent.h", "lower_graph.h", "linalg_cross_ops.h", "swapaxes_ops.h", "_foreach_sign.h", "zeros_compositeexplicitautograd_dispatch.h", "crow_indices_copy_native.h", "VirtualGuardImpl.h", "_cholesky_solve_helper_native.h", "cuda_random.h", "max_pool1d_with_indices.h", "hypot.h", "_segment_reduce_backward_cuda_dispatch.h", "mv_ops.h", "_embedding_bag_sparse_backward.h", "Flags.h", "vision.h", "indices_copy_ops.h", "_upsample_nearest_exact3d_meta.h", "check_alias_annotation.h", "linalg_matrix_power.h", "_neg_view_copy_native.h", "_efficientzerotensor_cpu_dispatch.h", "static_tracepoint_elfx86.h", "_sparse_csr_sum_native.h", "linalg_matrix_rank_ops.h", "logical_not_ops.h", "avg_pool2d_compositeexplicitautogradnonfunctional_dispatch.h", "ir.h", "_sparse_coo_tensor_with_dims_meta_dispatch.h", "LegacyVmapTransforms.h", "expm1_meta.h", "diagonal_native.h", "nll_loss_forward_cpu_dispatch.h", "adaptive_avg_pool3d_ops.h", "type_as.h", "resize_as_native.h", "codegen.h", "q_per_channel_zero_points_native.h", "std_mean_compositeimplicitautograd_dispatch.h", "_cudnn_rnn_native.h", "native_group_norm_backward_compositeexplicitautograd_dispatch.h", "randint.h", "sym_numel_native.h", "rrelu_with_noise_backward_ops.h", "stateful.h", "_to_sparse_compositeexplicitautograd_dispatch.h", "pytypes.h", "ccol_indices_copy.h", "hsplit.h", "_version_ops.h", "im2col.h", "xor_native.h", "MPSGraphVenturaOps.h", "sym_size_ops.h", "special_psi.h", "_to_sparse_bsr_cuda_dispatch.h", "_rowwise_prune.h", "linalg_eigvalsh_ops.h", "rref_proto.h", "nll_loss_native.h", "sendrpc_backward.h", "_pad_packed_sequence.h", "div_native.h", "addcmul_native.h", "native_norm_native.h", "CudaIPCTypes.h", "modulelist.h", "var_ops.h", "functional.h", "_masked_softmax_native.h", "_triton_multi_head_attention_compositeexplicitautograd_dispatch.h", "block_codegen.h", "ReductionType.h", "grad_layout_contract.h", "_grid_sampler_2d_cpu_fallback_ops.h", "unsafe_split_native.h", "triu_indices.h", "take_along_dim.h", "_make_dep_token_ops.h", "float_power_ops.h", "transformerlayer.h", "unfold_copy_native.h", "embedding_native.h", "miopen_convolution_compositeexplicitautograd_dispatch.h", "_efficient_attention_forward_native.h", "resize_as_compositeexplicitautograd_dispatch.h", "hardswish.h", "_aminmax.h", "meshgrid.h", "jit_opt_limit.h", "set_native.h", "dynamic_ir.h", "relu_native.h", "_validate_sparse_csc_tensor_args.h", "llvm_jit.h", "expm1_ops.h", "kaiser_window_compositeexplicitautograd_dispatch.h", "_empty_affine_quantized_cpu_dispatch.h", "_validate_compressed_sparse_indices.h", "type_hashing.h", "norm_cuda_dispatch.h", "fractional_max_pool2d_backward_ops.h", "nanquantile.h", "CUDAHooksInterface.h", "miopen_convolution_transpose.h", "grid_sampler_2d.h", "set_data.h", "fuse_linear.h", "reduce_on_plateau_scheduler.h", "is_coalesced_ops.h", "split_with_sizes_copy_ops.h", "hardtanh_backward_ops.h", "glu_backward_native.h", "special_gammaln_ops.h", "fuse_relu.h", "export.h", "bitwise_and.h", "lu_unpack_meta.h", "special_modified_bessel_k1_native.h", "expand_native.h", "logical_xor.h", "bitwise_left_shift_native.h", "GridSampler.h", "CuFFTUtils.h", "mH_native.h", "linalg_matrix_power_ops.h", "TensorSubclassLikeUtils.h", "align_tensors.h", "rpc_with_profiling_req.h", "rad2deg.h", "DeprecatedTypeProperties.h", "_sparse_log_softmax_compositeimplicitautograd_dispatch.h", "clip_native.h", "_fft_c2r_ops.h", "histogram_native.h", "_validate_sparse_compressed_tensor_args.h", "lstm_mps_backward_compositeexplicitautograd_dispatch.h", "autocast.h", "_spdiags_ops.h", "data.h", "upsample_bilinear2d_compositeexplicitautogradnonfunctional_dispatch.h", "argmax_cpu_dispatch.h", "ParallelOpenMP.h", "upsample_linear1d_backward_meta_dispatch.h", "_pad_enum_compositeimplicitautograd_dispatch.h", "fft_ihfft2_compositeimplicitautograd_dispatch.h", "_pack_padded_sequence.h", "empty_strided_cpu_dispatch.h", "trace_native.h", "_thnn_fused_gru_cell.h", "grid_sampler_3d_backward.h", "true_divide_native.h", "_amp_update_scale.h", "_values_copy_native.h", "addcdiv.h", "log2_ops.h", "unique_dim.h", "special_gammaincc_ops.h", "dynamic_type.h", "infer_schema.h", "propagate_gradients_req.h", "_foreach_minimum.h", "CachingHostAllocator.h", "zeros_native.h", "parameterdict.h", "subtract.h", "pimpl-inl.h", "inverse_native.h", "instancenorm.h", "amin.h", "empty.h", "avg_pool3d_backward_cuda_dispatch.h", "and_ops.h", "_dim_arange_ops.h", "pin_memory_ops.h", "TensorIterator.h", "adaptive_avg_pool3d_backward_ops.h", "linalg_lu_factor_ex.h", "multi_margin_loss_cuda_dispatch.h", "vsx_helpers.h", "_dim_arange_native.h", "slice_scatter_ops.h", "ReduceOpsUtils.h", "linalg_slogdet_ops.h", "tensorexpr_fuser.h", "Pool.h", "batch_norm_backward_reduce_compositeexplicitautograd_dispatch.h", "batch_norm_gather_stats_native.h", "fbgemm_linear_quantize_weight.h", "gru_cell_compositeimplicitautograd_dispatch.h", "linalg_matrix_rank_native.h", "IListRef.h", "_foreach_sign_ops.h", "fft_hfft_native.h", "nll_loss2d.h", "_ctc_loss_ops.h", "_empty_per_channel_affine_quantized.h", "softshrink_ops.h", "hsplit_ops.h", "python_tuples.h", "_embedding_bag_dense_backward_compositeexplicitautograd_dispatch.h", "_upsample_nearest_exact3d_backward_ops.h", "_unsafe_index_put_native.h", "_foreach_lerp_native.h", "take_native.h", "expand.h", "_scaled_mm_native.h", "_upsample_bicubic2d_aa_backward_compositeexplicitautogradnonfunctional_dispatch.h", "method.h", "complex_native.h", "_upsample_bicubic2d_aa_backward_native.h", "hardsigmoid_meta.h", "numpy.h", "_masked_softmax_backward.h", "imag_ops.h", "special_ndtr_ops.h", "addcdiv_ops.h", "CUDAAlgorithm.h", "nll_loss2d_backward_ops.h", "_fake_quantize_learnable_per_tensor_affine.h", "mkldnn_adaptive_avg_pool2d_backward_ops.h", "hardshrink_native.h", "native_group_norm_native.h", "as_strided_scatter_native.h", "max_pool3d_with_indices_native.h", "geqrf_native.h", "_nested_sum_backward_native.h", "fbgemm_linear_int8_weight_ops.h", "native_group_norm_cpu_dispatch.h", "alpha_dropout_native.h", "flatten_dense_tensors_ops.h", "Math.h", "tan_native.h", "input_buffer.h", "mkldnn_linear_backward.h", "uniform.h", "UndefinedTensorImpl.h", "NativeFunctions.h", "ravel_ops.h", "is_floating_point_native.h", "gru_native.h", "Array.h", "range_ops.h", "_euclidean_dist_native.h", "_compute_linear_combination.h", "_upsample_nearest_exact1d_backward_native.h", "sequencers.h", "fft_ihfftn_native.h", "_cast_Char_ops.h", "_unsafe_index_put.h", "bincount_ops.h", "_upsample_nearest_exact2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_make_dep_token_cpu_dispatch.h", "rref_context.h", "vec256_complex_float_vsx.h", "leaky_relu_backward_meta.h", "linalg_pinv_compositeimplicitautograd_dispatch.h", "cosine_similarity.h", "mkldnn_linear_backward_input.h", "permute_copy.h", "multinomial.h", "multinomial_cpu_dispatch.h", "tril_native.h", "unflatten_dense_tensors.h", "avg_pool2d_ops.h", "floor.h", "_lstm_mps_native.h", "_shape_as_tensor.h", "normalization.h", "frozen_linear_folding.h", "upsample_bilinear2d_backward_meta_dispatch.h", "full_native.h", "FunctionalTensorWrapper.h", "replication_pad2d_backward_ops.h", "special_i0.h", "TensorDimApply.h", "_weight_norm_differentiable_backward_ops.h", "special_modified_bessel_i0_native.h", "remove_redundant_profiles.h", "clamp_meta.h", "mkldnn_linear_backward_weights_native.h", "std_cuda_dispatch.h", "_test_serialization_subcmul_native.h", "special_log1p.h", "_cslt_sparse_mm_ops.h", "copy_sparse_to_sparse_ops.h", "mish_backward_ops.h", "_empty_affine_quantized_native.h", "cudnn_batch_norm.h", "_scaled_mm.h", "_make_dual.h", "special_gammaln_native.h", "linalg_qr.h", "WeightNormKernel.h", "IndexKernelUtils.h", "expand_ops.h", "Dispatch.h", "cudnn_batch_norm_native.h", "_reshape_copy.h", "feature_alpha_dropout.h", "clamp.h", "feature_dropout.h", "retains_grad_native.h", "histc.h", "_pad_enum.h", "fake_quantize_per_channel_affine_cachemask_ops.h", "upsample_trilinear3d.h", "linalg_householder_product.h", "hash.h", "baddbmm_native.h", "max_pool2d_with_indices_native.h", "binomial_native.h", "nll_loss_backward_meta_dispatch.h", "_trilinear.h", "native_batch_norm_backward_cpu_dispatch.h", "pin_memory.h", "div_meta_dispatch.h", "_native_batch_norm_legit_no_training_native.h", "masked_select_ops.h", "_fw_primal_native.h", "flatten_dense_tensors.h", "isposinf.h", "q_zero_point_ops.h", "swapdims_native.h", "linalg_lu_native.h", "lowering_context.h", "SharedReduceOps.h", "slice_copy_native.h", "sparse_bsr_tensor.h", "vision.h", "abs.h", "upsample_linear1d_backward_native.h", "batch_norm_backward_elemt.h", "_test_functorch_fallback_native.h", "row_indices.h", "TensorImpl.h", "_assert_async_native.h", "replication_pad2d_ops.h", "sym_size_native.h", "nll_loss_backward_ops.h", "absolute.h", "_cufft_get_plan_cache_size.h", "exponential_meta_dispatch.h", "_to_sparse_bsc_ops.h", "refine_tuple_types.h", "mul_meta.h", "DistributionTemplates.h", "unsqueeze_ops.h", "logit_backward_cuda_dispatch.h", "linalg_svd_ops.h", "_cholesky_solve_helper.h", "stft_ops.h", "einsum.h", "special_hermite_polynomial_he_ops.h", "hstack_native.h", "conv.h", "tensor.h", "glu_backward_jvp.h", "log.h", "where_native.h", "special_digamma.h", "repeat_interleave_native.h", "_foreach_acos_native.h", "any_module_holder.h", "metrics.h", "atanh_ops.h", "Sorting.h", "special_i0e_ops.h", "_to_dense_native.h", "ger.h", "_validate_sparse_bsr_tensor_args.h", "matrix_exp.h", "replication_pad3d_native.h", "special_legendre_polynomial_p_native.h", "acosh_meta.h", "special_erfinv.h", "_cudnn_rnn_backward_cuda_dispatch.h", "hstack.h", "flip_native.h", "_validate_sparse_bsc_tensor_args_native.h", "threshold_meta.h", "kl_div.h", "Float8_e5m2.h", "elu_backward.h", "ldexp_native.h", "linalg_lstsq.h", "_linalg_check_errors_native.h", "UpSampleKernelAVXAntialias.h", "_trilinear_ops.h", "broadcast_to_native.h", "dist_native.h", "sparse_sampled_addmm_native.h", "DistributionTemplates.h", "bilinear.h", "miopen_batch_norm_compositeexplicitautograd_dispatch.h", "native_batch_norm_native.h", "_embedding_bag_per_sample_weights_backward_native.h", "detach.h", "autocast_mode.h", "LegacyBatchedTensorImpl.h", "_test_warn_in_autograd.h", "SequenceNumber.h", "_upsample_nearest_exact3d_ops.h", "erfinv.h", "rnn.h", "tensor_flatten.h", "backend_interface.h", "sparse_coo_tensor_compositeimplicitautograd_dispatch.h", "_linalg_svd_meta.h", "CUDAGuard.h", "_embedding_bag_backward.h", "coalesce_ops.h", "min_ops.h", "_sobol_engine_ff_ops.h", "_sparse_coo_tensor_unsafe_ops.h", "ParamsHash.h", "native_group_norm.h", "_nnpack_available.h", "ConstexprCrc.h", "_unsafe_view_ops.h", "bitwise_or_native.h", "miopen_convolution_add_relu_native.h", "mkldnn_convolution_ops.h", "qembeddingbag.h", "aminmax_native.h", "PythonFallbackKernel.h", "_foreach_maximum.h", "special_modified_bessel_i1_meta.h", "rmsprop.h", "_fw_primal_copy_native.h", "round.h", "searchsorted_ops.h", "mish.h", "addmv_native.h", "_masked_softmax_ops.h", "to_padded_tensor.h", "fbgemm_pack_gemm_matrix_fp16_ops.h", "upsample_bicubic2d_cpu_dispatch.h", "Generator.h", "exponential_native.h", "value_selecting_reduction_backward.h", "serialize.h", "cauchy.h", "uniform_compositeexplicitautograd_dispatch.h", "bincount_native.h", "unique_consecutive_cuda_dispatch.h", "BatchingMetaprogramming.h", "optimizer.h", "_cdist_forward_ops.h", "function.h", "_sobol_engine_ff.h", "mean.h", "sspaddmm_ops.h", "_make_per_channel_quantized_tensor_native.h", "to_sparse_ops.h", "_sparse_bsr_tensor_unsafe_native.h", "logspace_ops.h", "qscheme_native.h", "expm1_native.h", "data_ops.h", "group_norm_ops.h", "_to_copy_compositeexplicitautograd_dispatch.h", "empty_permuted_native.h", "profiling_record.h", "fake_quantize_per_tensor_affine_native.h", "inliner.h", "upsample_nearest2d_cpu_dispatch.h", "lbfgs.h", "MPSAllocator.h", "upsample_bilinear2d_backward_cpu_dispatch.h", "half_support.h", "sort_meta.h", "_embedding_bag_dense_backward_native.h", "hardsigmoid_backward_ops.h", "mkldnn_rnn_layer.h", "logit_native.h", "upsample_nearest2d_backward.h", "fbgemm_pack_quantized_matrix_native.h", "cauchy_cuda_dispatch.h", "_empty_affine_quantized_ops.h", "gelu_native.h", "fft_irfftn.h", "nll_loss_backward_native.h", "_sparse_mm_reduce_impl_backward_native.h", "hardshrink_backward.h", "replication_pad1d_backward_native.h", "to_sparse_csc.h", "slice_backward_ops.h", "refine_names_native.h", "empty_permuted_compositeexplicitautograd_dispatch.h", "fix_native.h", "hinge_embedding_loss_native.h", "native_dropout.h", "fft_ihfft_native.h", "_slow_conv2d_forward_cpu_dispatch.h", "addbmm_ops.h", "lift_fresh_copy_native.h", "_coalesce_ops.h", "dsplit_native.h", "_upsample_bicubic2d_aa_backward_ops.h", "DeviceGuard.h", "_cslt_sparse_mm_native.h", "nuclear_norm_ops.h", "size.h", "_softmax_backward_data_meta.h", "rrelu_with_noise_ops.h", "nansum_cuda_dispatch.h", "sparse_coo_tensor_ops.h", "fft_irfft_native.h", "python_rpc_handler.h", "_nnpack_spatial_convolution_native.h", "hstack_ops.h", "_foreach_erfc_native.h", "take_along_dim_native.h", "native_layer_norm_backward_compositeexplicitautograd_dispatch.h", "_fused_adam_cuda_dispatch.h", "init.h", "greater_equal.h", "positive.h", "special_i1_ops.h", "upsample_nearest1d_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_nearest1d_backward.h", "_foreach_trunc.h", "_slow_conv2d_forward_ops.h", "adaptive_max_pool2d_backward_ops.h", "_foreach_cos_native.h", "cartesian_prod_ops.h", "_sobol_engine_scramble_native.h", "_fused_adamw_compositeexplicitautograd_dispatch.h", "pairwise_distance.h", "mkldnn_convolution.h", "_upsample_nearest_exact3d.h", "cumulative_trapezoid_native.h", "_sample_dirichlet_native.h", "logit_cuda_dispatch.h", "mse_loss.h", "Utils.h", "Dispatcher.h", "avg_pool3d_meta.h", "quantized_gru_cell_ops.h", "fft_ihfftn_compositeimplicitautograd_dispatch.h", "_upsample_nearest_exact1d_backward_ops.h", "cummin_native.h", "special_bessel_y0_ops.h", "UnaryOps.h", "segment_reduce_cpu_dispatch.h", "_linalg_svd_compositeexplicitautogradnonfunctional_dispatch.h", "pad_sequence_native.h", "stateless.h", "_unique_native.h", "max_pool2d_with_indices_backward_native.h", "fractional_max_pool2d.h", "_cufft_clear_plan_cache_ops.h", "bincount.h", "_nested_view_from_buffer_native.h", "_segment_reduce_backward_native.h", "slice_scatter.h", "_saturate_weight_to_fp16_native.h", "fbgemm_pack_gemm_matrix_fp16.h", "_thnn_fused_lstm_cell_compositeexplicitautograd_dispatch.h", "tensor.h", "linalg_cross.h", "lift_fresh_ops.h", "_conj_physical_native.h", "special_ndtri_native.h", "orgqr_native.h", "_foreach_addcmul_ops.h", "sparse_mask_native.h", "quantize_per_tensor_native.h", "_foreach_sinh.h", "sinh_native.h", "smooth_l1_loss_native.h", "backend.h", "bucketize.h", "nansum_ops.h", "upsample_bicubic2d_native.h", "tensor_dtypes.h", "max_ops.h", "Storage.h", "miopen_rnn_backward_cuda_dispatch.h", "argsort.h", "heaviside_meta.h", "poisson_nll_loss_ops.h", "hamming_window.h", "_reshape_alias_copy.h", "rrelu_with_noise_meta_dispatch.h", "argmax_native.h", "hardtanh_native.h", "_sample_dirichlet.h", "trace_backward_ops.h", "arctanh_native.h", "rnn_relu_cell_native.h", "chunk.h", "loopnest_randomization.h", "convolution_backward_ops.h", "_upsample_nearest_exact2d_backward.h", "special_chebyshev_polynomial_t_meta.h", "Sort.h", "max_unpool2d_ops.h", "retain_grad_native.h", "_cdist_backward_native.h", "batch_norm_gather_stats_with_counts_cuda_dispatch.h", "amin_native.h", "upsample_bilinear2d_backward_ops.h", "batch_norm_backward_reduce_native.h", "special_chebyshev_polynomial_v_native.h", "logaddexp_ops.h", "strtod.h", "special_sinc_ops.h", "layer_norm_ops.h", "native_layer_norm_compositeexplicitautograd_dispatch.h", "isinf_native.h", "_use_cudnn_ctc_loss_ops.h", "_fft_r2c_native.h", "logdet_ops.h", "fmax_ops.h", "bernoulli_compositeexplicitautograd_dispatch.h", "vec256_complex_float.h", "index_fill_ops.h", "atanh.h", "new_empty_ops.h", "PadNd.h", "cumprod_backward.h", "cudnn_is_acceptable_ops.h", "int_repr_ops.h", "sparse_bsc_tensor_ops.h", "special_bessel_y0.h", "_histogramdd_from_bin_cts_ops.h", "linalg_svd_native.h", "special_bessel_j0_native.h", "_thnn_fused_lstm_cell_backward_impl.h", "align_to_ops.h", "conv_depthwise3d_ops.h", "rad2deg_native.h", "_to_copy_native.h", "calculate_necessary_args.h", "select_copy_native.h", "special_exp2_native.h", "is_same_size_ops.h", "_upsample_bilinear2d_aa_backward.h", "_validate_sparse_csr_tensor_args.h", "fractional_max_pool3d_backward.h", "python_dict.h", "sparse_resize_ops.h", "python_strings.h", "shape_function_registry.h", "ccol_indices_copy_native.h", "dot.h", "custom_operator.h", "_histogramdd_from_bin_cts_cpu_dispatch.h", "fft_hfft2_ops.h", "_validate_sparse_bsr_tensor_args_ops.h", "_indices_ops.h", "_weight_norm_interface_backward.h", "_test_optional_floatlist_native.h", "hardtanh_backward.h", "_weight_norm_interface.h", "operator_name.h", "_cudnn_rnn_backward.h", "mse_loss_backward_ops.h", "_upsample_nearest_exact1d_compositeimplicitautograd_dispatch.h", "deg2rad_ops.h", "nll_loss2d_backward.h", "multi_wait.h", "coalesce.h", "special.h", "_conj_copy_ops.h", "set_ops.h", "t_ops.h", "masked_scatter_ops.h", "amax.h", "equal_ops.h", "upsample_nearest3d_backward_meta.h", "floor_divide_native.h", "gcd_meta.h", "randn_like.h", "clip_compositeimplicitautograd_dispatch.h", "convolution_backward_cuda_dispatch.h", "atleast_2d.h", "nansum.h", "_test_optional_filled_intlist.h", "fft_rfft2_compositeimplicitautograd_dispatch.h", "ones_like_compositeexplicitautograd_dispatch.h", "_slow_conv2d_backward.h", "_cast_Short.h", "_transform_bias_rescale_qkv_ops.h", "_upsample_nearest_exact1d_backward_meta.h", "true_divide_ops.h", "lowerings.h", "_foreach_tan_native.h", "native_batch_norm_cpu_dispatch.h", "softplus_backward.h", "_scaled_dot_product_flash_attention_native.h", "_gather_sparse_backward.h", "bernoulli_ops.h", "cumprod.h", "mkldnn_reorder_conv2d_weight_native.h", "_scaled_dot_product_efficient_attention.h", "sparse_csr_tensor_native.h", "_sparse_sum.h", "python_variable_indexing.h", "quantize_per_tensor.h", "special_erf_ops.h", "row_indices_ops.h", "cummaxmin_backward_native.h", "_dimV_native.h", "tree.h", "linalg_eigh.h", "lift.h", "cumsum_meta.h", "irange.h", "_linalg_svd_meta_dispatch.h", "upsample_bilinear2d_cpu_dispatch.h", "xor.h", "view_as_ops.h", "row_indices_copy_native.h", "pad_native.h", "rot90.h", "scatter_add_meta.h", "kthvalue_ops.h", "class_type.h", "recvrpc_backward.h", "empty_quantized_compositeexplicitautograd_dispatch.h", "quantile.h", "upsample_nearest1d_backward_cuda_dispatch.h", "cudnn_batch_norm_backward_ops.h", "Storage.h", "embedding_backward_ops.h", "batch_norm_gather_stats_with_counts.h", "squeeze_copy_ops.h", "atan_meta.h", "script_remote_call.h", "_neg_view_ops.h", "hypot_ops.h", "numpy_T_ops.h", "functional.h", "relu6_native.h", "native_dropout_compositeexplicitautograd_dispatch.h", "kineto_shim.h", "Unroll.h", "or_ops.h", "full_like_ops.h", "_euclidean_dist_ops.h", "nested_to_padded_tensor_compositeimplicitautograd_dispatch.h", "_fake_quantize_learnable_per_tensor_affine_native.h", "_is_zerotensor_ops.h", "subgraph_matcher.h", "_unpack_dual.h", "_triton_multi_head_attention_ops.h", "mkldnn_linear_backward_weights.h", "_cudnn_rnn_flatten_weight_native.h", "multi_margin_loss_backward_cuda_dispatch.h", "std_cpu_dispatch.h", "reflection_pad1d_native.h", "multilabel_margin_loss_backward.h", "_fake_quantize_learnable_per_tensor_affine_ops.h", "cumprod_cpu_dispatch.h", "rrelu_with_noise_backward.h", "linear_compositeexplicitautograd_dispatch.h", "real.h", "arccos_ops.h", "miopen_convolution.h", "select_backward_ops.h", "aminmax_compositeexplicitautogradnonfunctional_dispatch.h", "fbgemm_linear_fp16_weight_fp32_activation_native.h", "shared.h", "frozen_conv_folding.h", "native_layer_norm.h", "col2im_ops.h", "_nested_view_from_buffer_copy_ops.h", "_histogramdd_bin_edges_ops.h", "frobenius_norm_native.h", "_convolution_double_backward.h", "mish_backward_native.h", "asin_ops.h", "upsample_bilinear2d.h", "_sparse_coo_tensor_with_dims_and_tensors_meta_dispatch.h", "_upsample_nearest_exact3d_backward.h", "divide_ops.h", "addcmul_meta.h", "value_selecting_reduction_backward_native.h", "gather_backward_native.h", "EmbeddingBag.h", "polygamma_ops.h", "sinc_ops.h", "special_xlog1py_meta.h", "special_multigammaln_ops.h", "cummin.h", "_sparse_sparse_matmul.h", "logit_cpu_dispatch.h", "combinations_native.h", "frozen_conv_add_relu_fusion.h", "sum_to_size_ops.h", "pad_sequence_ops.h", "aminmax_cpu_dispatch.h", "hann_window_native.h", "smooth_l1_loss.h", "_add_relu_ops.h", "export_bytecode.h", "sym_stride_native.h", "detach_ops.h", "rrelu_ops.h", "instruction.h", "_to_dense_ops.h", "Function.h", "collate.h", "binary_cross_entropy_cuda_dispatch.h", "jit_utils.h", "bmm.h", "fixup_trace_scope_blocks.h", "debug_info.h", "_thnn_fused_lstm_cell_backward_impl_native.h", "linalg_norm.h", "_mkldnn_transpose_ops.h", "new_zeros.h", "special_sinc_native.h", "channel_shuffle_native.h", "rand_like_ops.h", "fft_ifft_native.h", "cloneable.h", "to_mkldnn_compositeexplicitautograd_dispatch.h", "fbgemm_linear_quantize_weight_native.h", "HIPGuardImplMasqueradingAsCUDA.h", "enum.h", "is_nonzero.h", "align_to.h", "worker_exception.h", "sin_native.h", "lt_meta.h", "fractional_max_pool3d_meta.h", "forward_grad.h", "slice_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_backward.h", "types.h", "lu_solve_native.h", "fractional_max_pool3d_ops.h", "_cudnn_rnn_backward_ops.h", "nll_loss2d_backward_cuda_dispatch.h", "distributed.h", "lstm_cell_ops.h", "_spdiags_native.h", "special_modified_bessel_i0_ops.h", "nll_loss.h", "CUDASparseDescriptors.h", "linalg_tensorsolve.h", "to_sparse_native.h", "helper.h", "diag_ops.h", "slice_copy.h", "gather.h", "isin_meta.h", "gru_ops.h", "nonzero_numpy.h", "less_native.h", "maximum_ops.h", "poisson_ops.h", "erfinv_meta.h", "logdet_native.h", "_conj_copy_native.h", "multinomial_cuda_dispatch.h", "cache.h", "sym_constrain_range_for_size_native.h", "ReduceAllOps.h", "unbind_copy_ops.h", "arctan2.h", "resize_as_sparse.h", "log_normal_native.h", "pow.h", "_scaled_dot_product_attention_math.h", "_nested_tensor_storage_offsets.h", "Interpreter.h", "MapAllocator.h", "tensor_impl.h", "expand_copy_ops.h", "histc_native.h", "StringUtil.h", "quantize_per_channel.h", "cudnn-wrapper.h", "_sample_dirichlet_compositeexplicitautograd_dispatch.h", "matmul.h", "t_native.h", "resize_as_ops.h", "native_norm_compositeexplicitautograd_dispatch.h", "uniform_meta_dispatch.h", "_efficient_attention_backward_native.h", "_nested_tensor_from_tensor_list_compositeexplicitautograd_dispatch.h", "adaptive_max_pool2d_backward_native.h", "mkldnn_rnn_layer_backward_native.h", "vml.h", "dropout_ops.h", "_upsample_nearest_exact1d_meta.h", "batch_norm_update_stats_native.h", "cummaxmin_backward.h", "linalg_svdvals_compositeimplicitautograd_dispatch.h", "_amp_foreach_non_finite_check_and_unscale_ops.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_native.h", "frobenius_norm.h", "to_mkldnn_backward_native.h", "to_sparse_csr_compositeimplicitautograd_dispatch.h", "index.h", "histogramdd_compositeimplicitautograd_dispatch.h", "fft_fftfreq_compositeexplicitautograd_dispatch.h", "xnnpack.h", "rrelu_with_noise_backward_native.h", "conv_transpose2d_compositeimplicitautograd_dispatch.h", "uniform_cpu_dispatch.h", "special_xlogy.h", "median_ops.h", "unpickled_python_remote_call.h", "_upsample_nearest_exact3d_backward_meta.h", "topk.h", "vdot.h", "_to_sparse_semi_structured_native.h", "set_data_ops.h", "ltc_ops.h", "contiguous.h", "_adaptive_avg_pool3d_ops.h", "_to_cpu_native.h", "special_hermite_polynomial_h_meta.h", "CuFFTPlanCache.h", "to_sparse_bsr_compositeimplicitautograd_dispatch.h", "lstm_mps_backward.h", "_upsample_nearest_exact1d_cuda_dispatch.h", "cholesky.h", "trunc.h", "empty_strided_meta_dispatch.h", "special_log_ndtr.h", "logical_or_native.h", "reshape_native.h", "_make_dual_native.h", "count_nonzero_ops.h", "margin_ranking_loss_native.h", "_to_sparse_ops.h", "kl_div_native.h", "multilabel_margin_loss_backward_native.h", "_foreach_minimum_ops.h", "i0_ops.h", "silu.h", "frozen_concat_linear.h", "to_sparse_csc_compositeimplicitautograd_dispatch.h", "rrelu_with_noise_cuda_dispatch.h", "unsafe_split.h", "rsqrt_ops.h", "special_zeta_native.h", "nonzero_native.h", "affine_grid_generator_backward_native.h", "grid_sampler_3d.h", "adaptive_max_pool3d.h", "_foreach_copy.h", "sugared_value.h", "import_export_common.h", "_sparse_semi_structured_linear_cuda_dispatch.h", "mul_native.h", "_nested_tensor_storage_offsets_native.h", "DeviceGuard.h", "imag_native.h", "angle_ops.h", "PointwiseOps.h", "quantized_max_pool3d_ops.h", "fft_rfft_ops.h", "upsample_nearest3d_native.h", "fft_irfftn_compositeimplicitautograd_dispatch.h", "GeneratorForPrivateuseone.h", "positive_ops.h", "conv_transpose2d.h", "expand_as_native.h", "UnfoldBackward.h", "tensor_split.h", "concat_native.h", "to_mkldnn_native.h", "any.h", "to_sparse_bsr_ops.h", "special_modified_bessel_i1.h", "align_as_native.h", "_foreach_round_native.h", "CUDAContext.h", "stmt.h", "Size.h", "col_indices_ops.h", "all.h", "norm_except_dim.h", "diff.h", "atanh_meta.h", "equal.h", "_masked_softmax_backward_cpu_dispatch.h", "upsample_bicubic2d_backward_ops.h", "function_impl.h", "special_bessel_j1_native.h", "index_select_backward_native.h", "_resize_output.h", "bilinear_native.h", "index_reduce.h", "_cast_Char_native.h", "python_custom_class.h", "blackman_window.h", "complex_math.h", "miopen_rnn.h", "_sparse_bsc_tensor_unsafe_native.h", "variable_tensor_list.h", "binary_cross_entropy_with_logits_native.h", "cudnn_grid_sampler_backward.h", "count_nonzero_native.h", "inverse_ops.h", "_sparse_sparse_matmul_native.h", "_linalg_eigh_meta.h", "_foreach_maximum_native.h", "exit_transforms.h", "mean_cpu_dispatch.h", "swapaxes.h", "special_entr.h", "adaptive_max_pool3d_backward_native.h", "nextafter_meta.h", "quantized_rnn_relu_cell.h", "_sparse_semi_structured_linear_native.h", "_test_autograd_multiple_dispatch.h", "max_pool2d_ops.h", "ones.h", "tanh_backward.h", "ir_emitter.h", "special_bessel_j1_ops.h", "max_pool1d_native.h", "List_inl.h", "_debug_has_internal_overlap_native.h", "_embedding_bag_dense_backward_cuda_dispatch.h", "upsample_trilinear3d_backward_ops.h", "poisson_cuda_dispatch.h", "atleast_1d.h", "RangeFactories.h", "constant_pooling.h", "outer.h", "permute.h", "index_select.h", "linalg_multi_dot_ops.h", "_convolution_double_backward_native.h", "special_shifted_chebyshev_polynomial_t.h", "python_numbers.h", "backend_preprocess.h", "_upsample_nearest_exact2d_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_qr_meta.h", "conv3d.h", "gather_meta.h", "poisson_nll_loss_native.h", "_fw_primal_copy.h", "_propagate_xla_data.h", "_histogramdd_from_bin_tensors_native.h", "thread_constants.h", "logcumsumexp.h", "std_mean.h", "max_unpool2d.h", "_grid_sampler_2d_cpu_fallback_backward_ops.h", "InlineDeviceGuard.h", "softplus_ops.h", "matmul_ops.h", "_foreach_clamp_max_native.h", "_to_sparse_csr_compositeexplicitautograd_dispatch.h", "hypot_native.h", "flatbuffer_serializer.h", "can_cast.h", "graph_executor.h", "special_digamma_native.h", "_adaptive_avg_pool2d_ops.h", "quantized_lstm_cell_ops.h", "cudnn_convolution_add_relu.h", "TensorMeta.h", "_upsample_nearest_exact3d_cuda_dispatch.h", "pairwise_distance_ops.h", "_coalesce.h", "_validate_sparse_coo_tensor_args_ops.h", "_validate_sparse_coo_tensor_args_compositeimplicitautograd_dispatch.h", "_values_ops.h", "rnn_relu_ops.h", "l1_loss.h", "frexp_native.h", "mkldnn_max_pool2d_backward_native.h", "put_ops.h", "Half.h", "eq_ops.h", "cdist_compositeimplicitautograd_dispatch.h", "_thnn_fused_lstm_cell_native.h", "lambda.h", "_upsample_nearest_exact2d_backward_cpu_dispatch.h", "python_cpp_function.h", "linalg_eigh_native.h", "_mkldnn_reshape.h", "transpose_ops.h", "fft_ifft2_ops.h", "upsample_trilinear3d_backward_meta.h", "scaled_dot_product_attention_native.h", "_cslt_compress_native.h", "tracer.h", "embedding_bag_ops.h", "_weight_norm_native.h", "batch_norm_compositeimplicitautograd_dispatch.h", "embedding_sparse_backward_native.h", "linalg_eigh_ops.h", "transpose_copy.h", "convolution_backward_native.h", "_to_sparse_csc.h", "lgamma.h", "_to_sparse_csc_cpu_dispatch.h", "lshift_ops.h", "_pdist_backward_native.h", "histogram_ops.h", "tril_ops.h", "_sparse_mm_native.h", "qscheme.h", "rnn_relu_cell_ops.h", "smooth_l1_loss_backward_ops.h", "special_hermite_polynomial_h_ops.h", "fractional_max_pool3d_native.h", "UniqueVoidPtr.h", "_fft_r2c_ops.h", "embedding_sparse_backward.h", "quantized_lstm_cell.h", "cosine_embedding_loss_ops.h", "init.h", "_pad_circular.h", "kthvalue_native.h", "linalg_inv_ex_native.h", "native_group_norm_cuda_dispatch.h", "_foreach_erf_ops.h", "acosh_native.h", "adamw.h", "_standard_gamma.h", "igammac.h", "empty_permuted_ops.h", "_embedding_bag_dense_backward.h", "fake_quantize_per_tensor_affine.h", "_empty_per_channel_affine_quantized_native.h", "output_nr_ops.h", "special_log_ndtr_ops.h", "_grid_sampler_2d_cpu_fallback_native.h", "linear_backward.h", "tensor_list.h", "_foreach_zero.h", "addmv.h", "hann_window.h", "OptionalArrayRef.h", "inner_native.h", "clone_compositeexplicitautograd_dispatch.h", "slogdet.h", "trapz_native.h", "special_scaled_modified_bessel_k0_native.h", "vulkan.h", "mkldnn_convolution_compositeexplicitautograd_dispatch.h", "_foreach_sinh_ops.h", "tensor_apply.h", "selu_native.h", "multilabel_margin_loss_forward_native.h", "lambda_post_hook.h", "unflatten_native.h", "Normalization.h", "Loops.h", "special_erfcx_meta.h", "_transformer_encoder_layer_fwd_compositeexplicitautograd_dispatch.h", "div.h", "utils.h", "upsample_linear1d_backward_meta.h", "fill_ops.h", "fft_fftn_ops.h", "tile.h", "exponential_ops.h", "_cdist_forward_compositeexplicitautograd_dispatch.h", "bitwise_right_shift_ops.h", "new_empty_compositeexplicitautograd_dispatch.h", "_sobol_engine_draw_native.h", "_foreach_ceil_ops.h", "upsample_nearest1d_cuda_dispatch.h", "normal_meta_dispatch.h", "pow_ops.h", "max_pool1d_with_indices_ops.h", "_functional_sym_constrain_range_ops.h", "linalg_lu_factor_native.h", "ir_cloner.h", "mode_ops.h", "silu_backward_native.h", "to_sparse_compositeimplicitautograd_dispatch.h", "geometric_native.h", "_upsample_bilinear2d_aa_compositeimplicitautograd_dispatch.h", "glu_meta.h", "cross.h", "requires_grad_analysis.h", "bmm_meta.h", "_indices.h", "scatter_reduce_meta.h", "fbgemm_linear_int8_weight_native.h", "igammac_ops.h", "_to_sparse_bsc_cpu_dispatch.h", "nanmedian_native.h", "avg_pool3d_cuda_dispatch.h", "pin_memory_native.h", "_unsafe_index_ops.h", "sym_constrain_range_compositeexplicitautograd_dispatch.h", "upsample_bilinear2d_ops.h", "_thnn_fused_lstm_cell_cuda_dispatch.h", "cpp_stacktraces.h", "hann_window_ops.h", "aten_interned_strings.h", "crow_indices_ops.h", "propagate_gradients_resp.h", "nan_to_num_cpu_dispatch.h", "upsample_nearest3d_compositeimplicitautograd_dispatch.h", "linalg_cholesky_ex_ops.h", "result_type_native.h", "fft_fft2_native.h", "linalg_vector_norm_cuda_dispatch.h", "upsample_bilinear2d_cuda_dispatch.h", "fmax_native.h", "multiply.h", "convolution_backward_compositeexplicitautograd_dispatch.h", "conv_tbc_backward_native.h", "mkldnn_linear.h", "autodiff.h", "linalg_slogdet.h", "linalg_vander_compositeimplicitautograd_dispatch.h", "_foreach_norm.h", "multi_margin_loss_backward_cpu_dispatch.h", "_test_optional_intlist_ops.h", "import_data.h", "linalg_cond_ops.h", "istft_native.h", "_embedding_bag_compositeexplicitautograd_dispatch.h", "quantized_max_pool1d_ops.h", "outer_native.h", "_cast_Double_ops.h", "flat_hash_map.h", "flatten_ops.h", "gt_native.h", "special_shifted_chebyshev_polynomial_v.h", "isposinf_meta.h", "MPSStream.h", "soft_margin_loss_backward.h", "rand_like_compositeexplicitautograd_dispatch.h", "_linalg_slogdet_ops.h", "slow_conv_transpose2d_native.h", "ParamUtils.h", "output_nr_native.h", "grid_sampler.h", "hardsigmoid_backward_native.h", "typeid.h", "unique_consecutive_native.h", "_thnn_fused_gru_cell_native.h", "feature_alpha_dropout_ops.h", "binomial_ops.h", "_validate_sparse_compressed_tensor_args_ops.h", "reflection_pad3d_backward_ops.h", "mse_loss_meta.h", "linalg_eigvalsh.h", "_sobol_engine_draw_compositeimplicitautograd_dispatch.h", "Padding.h", "internals.h", "pointwise.h", "masked_scatter.h", "vsplit_ops.h", "isneginf_native.h", "special_chebyshev_polynomial_w_ops.h", "vstack_native.h", "normalization.h", "convolution_backward.h", "adaptive_avg_pool2d.h", "special_polygamma_ops.h", "batch_norm_gather_stats_with_counts_native.h", "symbol.h", "istft_ops.h", "xlogy.h", "masked_fill_ops.h", "_unique2_native.h", "eq_meta.h", "_sparse_bsr_tensor_unsafe.h", "float_power_native.h", "infinitely_differentiable_gelu_backward.h", "miopen_batch_norm_backward_compositeexplicitautograd_dispatch.h", "is_neg_ops.h", "mkldnn_linear_backward_input_native.h", "erase_number_types.h", "asinh_meta.h", "_native_multi_head_attention_cuda_dispatch.h", "normal_ops.h", "_spdiags_compositeexplicitautograd_dispatch.h", "bitwise_and_meta.h", "max_pool1d.h", "IdWrapper.h", "_fake_quantize_learnable_per_channel_affine_backward_ops.h", "max_pool2d_with_indices_backward_meta.h", "special_logit_ops.h", "canonicalize_modified_loop.h", "QScheme.h", "shape_analysis.h", "_propagate_xla_data_native.h", "cauchy_compositeexplicitautograd_dispatch.h", "_thnn_differentiable_lstm_cell_backward_compositeimplicitautograd_dispatch.h", "inner_ops.h", "column_stack.h", "_sparse_coo_tensor_with_dims_and_tensors.h", "grid_sampler_2d_native.h", "_native_batch_norm_legit_ops.h", "ir.h", "pdist_native.h", "special_round.h", "Dict_inl.h", "_linalg_svd_cuda_dispatch.h", "callstack_debug_info_serialization.h", "CUDAException.h", "infinitely_differentiable_gelu_backward_native.h", "special_ndtr.h", "_upsample_nearest_exact2d_backward_ops.h", "canonicalize.h", "logical_and_native.h", "_upsample_bilinear2d_aa_ops.h", "is_distributed_native.h", "index_reduce_ops.h", "logit_backward.h", "_nested_select_backward_native.h", "nonzero_static_native.h", "clamp_max_meta.h", "TensorNames.h", "IListRef_inl.h", "tensor_util.h", "_cast_Short_ops.h", "CUDADeviceAssertionHost.h", "new_zeros_native.h", "AccumulateType.h", "_resize_output_ops.h", "split_with_sizes_copy_native.h", "_efficient_attention_backward_ops.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_ops.h", "_triton_scaled_dot_attention_ops.h", "flatten_native.h", "linalg_cholesky_ops.h", "atan.h", "sigmoid_backward_ops.h", "_nested_tensor_from_mask_left_aligned.h", "prod_meta_dispatch.h", "TypeDefault.h", "div_compositeexplicitautograd_dispatch.h", "python_util.h", "upsample_bilinear2d_meta.h", "_remove_batch_dim_ops.h", "special_sinc.h", "fft_rfft_native.h", "batch_norm_backward_reduce.h", "CPUFallback.h", "cdist_native.h", "softshrink_backward_meta.h", "llvm_codegen.h", "miopen_depthwise_convolution_compositeexplicitautograd_dispatch.h", "constant_pad_nd_ops.h", "special_scaled_modified_bessel_k0_meta.h", "huber_loss_ops.h", "linalg_ldl_solve.h", "upsample_nearest2d_native.h", "alias.h", "special_chebyshev_polynomial_u_meta.h", "_sparse_mm_reduce_impl_ops.h", "rshift_ops.h", "linalg_lu_solve_ops.h", "count_nonzero.h", "error.h", "quantile_native.h", "onednn_graph_fuser.h", "logdet.h", "argmax_meta_dispatch.h", "ScopeExit.h", "sum_cpu_dispatch.h", "pixel_shuffle.h", "_cufft_set_plan_cache_max_size_native.h", "col2im.h", "fft_rfftfreq_compositeexplicitautograd_dispatch.h", "misc.h", "OpaqueTensorImpl.h", "named_value.h", "true_divide.h", "_grid_sampler_2d_cpu_fallback.h", "gelu_backward_ops.h", "_validate_sparse_bsc_tensor_args_ops.h", "binary_cross_entropy_backward_cpu_dispatch.h", "fold_linear_bn.h", "Registry.h", "rad2deg_ops.h", "_gather_sparse_backward_ops.h", "fft_irfft2_ops.h", "update_graph_executor_opt.h", "_scaled_dot_product_efficient_attention_cuda_dispatch.h", "selu.h", "nanmean.h", "_dimI.h", "q_per_channel_scales_ops.h", "special_xlog1py_ops.h", "python_function.h", "special_ndtri_ops.h", "tanh_backward_native.h", "string_view.h", "gather_ops.h", "adaptive_max_pool2d_meta.h", "new_full_compositeexplicitautograd_dispatch.h", "linalg_solve_ops.h", "_reshape_copy_native.h", "view_as_real_ops.h", "_pack_padded_sequence_backward.h", "_amp_update_scale_native.h", "nextafter.h", "TypeList.h", "special_shifted_chebyshev_polynomial_u_meta.h", "concat_ops.h", "norm_ops.h", "linalg_vander_native.h", "blackman_window_native.h", "upsample_nearest3d_backward_native.h", "transformerlayer.h", "from_file_cpu_dispatch.h", "nanmean_native.h", "from_blob.h", "inline_fork_wait.h", "graph_executor_impl.h", "celu_native.h", "adaptive_avg_pool1d.h", "_validate_sparse_bsr_tensor_args_native.h", "upsample_bilinear2d_compositeimplicitautograd_dispatch.h", "_sparse_broadcast_to_copy.h", "_sparse_csr_tensor_unsafe.h", "index_select_backward_ops.h", "istft.h", "row_stack_native.h", "TensorAdvancedIndexingUtils.h", "update_differentiable_graph_requires_grad.h", "conv_transpose2d_ops.h", "tanh_ops.h", "linalg_qr_ops.h", "_foreach_addcmul.h", "bit_cast.h", "lgamma_native.h", "ConstantSymNodeImpl.h", "_efficient_attention_backward_cuda_dispatch.h", "_convolution_mode.h", "huber_loss_backward_ops.h", "_assert_tensor_metadata.h", "_fused_moving_avg_obs_fq_helper_ops.h", "variable_factories.h", "miopen_batch_norm_backward_ops.h", "log10.h", "reflection_pad2d.h", "_cufft_clear_plan_cache_native.h", "unflatten_dense_tensors_ops.h", "cos_ops.h", "upsample_nearest1d_backward_ops.h", "upsample_trilinear3d_backward_cuda_dispatch.h", "ne_meta.h", "range.h", "utils.h", "upsample_nearest2d_meta.h", "file_format.h", "view_as_real_native.h", "matmul_backward.h", "Dict.h", "unbind_ops.h", "sparse_resize_native.h", "thnn_conv2d_native.h", "inverse.h", "_cdist_backward.h", "NonSymbolicBC.h", "prelu.h", "python_special_functions.h", "full_like_native.h", "binary_cross_entropy_backward_ops.h", "conv1d_ops.h", "broadcast_tensors_ops.h", "special_hermite_polynomial_he_meta.h", "bitwise_left_shift_ops.h", "_to_sparse.h", "_nested_from_padded_and_nested_example_native.h", "special_airy_ai_meta.h", "_foreach_reciprocal_ops.h", "to_sparse.h", "upsample_nearest2d_cuda_dispatch.h", "divide_compositeimplicitautograd_dispatch.h", "is_pinned_ops.h", "DynamicTypes.h", "atan2_native.h", "amax_native.h", "_nested_tensor_storage_offsets_ops.h", "_thnn_fused_lstm_cell_backward.h", "_fused_sdp_choice.h", "tanh_backward_ops.h", "_to_copy_ops.h", "Metaprogramming.h", "scatter_add_ops.h", "tanh_meta.h", "mps_convolution_transpose_backward.h", "q_per_channel_zero_points_ops.h", "upsample_trilinear3d_backward_native.h", "upsample_nearest3d_compositeexplicitautogradnonfunctional_dispatch.h", "stack.h", "special_entr_native.h", "peephole.h", "_reshape_alias_copy_ops.h", "versioned_symbols.h", "to_padded_tensor_native.h", "_triton_scaled_dot_attention.h", "native_batch_norm_backward_native.h", "PythonOpRegistrationTrampoline.h", "avg_pool2d_backward_native.h", "special_modified_bessel_i0.h", "Backend.h", "ge.h", "nested_to_padded_tensor_ops.h", "fft_rfftfreq_ops.h", "fbgemm_linear_fp16_weight_ops.h", "special_bessel_j0_meta.h", "cudnn_grid_sampler_backward_native.h", "utils.h", "is_floating_point_ops.h", "sign.h", "grid_sampler_native.h", "sum_native.h", "_upsample_bicubic2d_aa_ops.h", "_backward_ops.h", "ctc_loss_ops.h", "_upsample_nearest_exact3d_backward_cuda_dispatch.h", "intrusive_ptr.h", "fft_ihfft_compositeimplicitautograd_dispatch.h", "var.h", "BinaryInternal.h", "channel_shuffle_ops.h", "_to_sparse_bsr_native.h", "_validate_sparse_csr_tensor_args_native.h", "slow_conv3d_forward_cpu_dispatch.h", "ir_builder.h", "custom_class.h", "specialize_autogradzero.h", "nuclear_norm_native.h", "_thnn_fused_lstm_cell_backward_impl_cuda_dispatch.h", "upsample_linear1d_cpu_dispatch.h", "NamedTensorUtils.h", "_sparse_softmax_compositeimplicitautograd_dispatch.h", "hardshrink.h", "_make_dual_copy.h", "mkldnn_convolution_native.h", "reflection_pad3d_backward.h", "narrow_copy.h", "_scaled_dot_product_efficient_attention_backward_cuda_dispatch.h", "eye_ops.h", "nll_loss_backward_meta.h", "TensorIndexing.h", "embedding_dense_backward.h", "fbgemm_linear_int8_weight_fp32_activation_native.h", "linalg_tensorsolve_compositeimplicitautograd_dispatch.h", "arcsin_native.h", "_upsample_nearest_exact2d_meta_dispatch.h", "max_pool2d_with_indices.h", "_scaled_dot_product_flash_attention.h", "_embedding_bag_forward_only_compositeexplicitautograd_dispatch.h", "batchnorm.h", "nested.h", "_logcumsumexp.h", "register_packed_params.h", "_cast_Byte.h", "linalg_solve_ex_ops.h", "fft_ifft_compositeimplicitautograd_dispatch.h", "GridSampler.h", "special_hermite_polynomial_he.h", "vstack_ops.h", "_linalg_det.h", "convolution_overrideable_compositeexplicitautograd_dispatch.h", "storage_context.h", "fractional_max_pool3d_backward_ops.h", "var_compositeimplicitautograd_dispatch.h", "multi_margin_loss.h", "thnn_conv2d_ops.h", "alpha_dropout_ops.h", "logical_and.h", "q_zero_point.h", "miopen_rnn_cuda_dispatch.h", "hardswish_backward.h", "index_put_native.h", "chain_matmul.h", "refine_names.h", "_values.h", "less_ops.h", "DefaultTensorOptions.h", "reflection_pad1d_backward_native.h", "multi_margin_loss_backward.h", "narrow_ops.h", "_foreach_pow_native.h", "ordered_dict.h", "row_indices_copy_ops.h", "triplet_margin_loss.h", "fft_ihfftn_ops.h", "cos_native.h", "_test_optional_floatlist.h", "in_memory_adapter.h", "signbit_meta.h", "fractional_max_pool2d_backward_native.h", "special_chebyshev_polynomial_w_native.h", "nll_loss_nd_native.h", "FunctionsManual.h", "_index_put_impl_meta_dispatch.h", "_test_warn_in_autograd_native.h", "cudnn_grid_sampler_native.h", "cudnn_batch_norm_ops.h", "_embedding_bag_forward_only_cpu_dispatch.h", "_nested_tensor_from_mask_ops.h", "new_empty_strided.h", "bitwise_left_shift.h", "rand_ops.h", "_foreach_sigmoid_native.h", "request_callback_no_python.h", "_functional_assert_async_ops.h", "_sparse_softmax_ops.h", "view_copy_native.h", "_linalg_slogdet_native.h", "_upsample_nearest_exact2d_backward_cuda_dispatch.h", "argwhere_native.h", "cartesian_prod_native.h", "special_shifted_chebyshev_polynomial_v_native.h", "leaky_relu_backward.h", "multi_margin_loss_ops.h", "special_i1e_ops.h", "cross_entropy_loss_ops.h", "concatenate_native.h", "xlogy_native.h", "searchsorted_cuda_dispatch.h", "conv_transpose3d.h", "fft_hfft_ops.h", "ge_ops.h", "special_logit_native.h", "_functional_sym_constrain_range_native.h", "_convolution_mode_ops.h", "_sparse_softmax_backward_data_native.h", "transpose.h", "retains_grad_ops.h", "special_psi_native.h", "detach_copy_ops.h", "ivalue_inl.h", "_cast_Half_ops.h", "cholesky_inverse_native.h", "_sparse_sum_backward_ops.h", "_mkldnn_transpose_native.h", "_nested_sum_backward.h", "value_refinement_utils.h", "function.h", "batch_norm.h", "_upsample_bilinear2d_aa.h", "lift_fresh.h", "det_native.h", "_upsample_bicubic2d_aa_meta_dispatch.h", "affine_grid_generator_backward_ops.h", "_histogramdd_bin_edges.h", "zeros_like_compositeexplicitautograd_dispatch.h", "vec256_bfloat16.h", "bernoulli_cuda_dispatch.h", "rref_backward_req.h", "_foreach_div_native.h", "norm.h", "output_nr.h", "lgamma_meta.h", "view_as_complex_copy.h", "cudnn_affine_grid_generator_native.h", "_sobol_engine_scramble_ops.h", "OnednnUtils.h", "KernelFunction_impl.h", "_linalg_eigh_ops.h", "lerp_ops.h", "fft_irfft2.h", "trapezoid.h", "serialized_shape_function_registry.h", "_logcumsumexp_ops.h", "unsqueeze_copy.h", "quantized_max_pool3d.h", "clamp_cpu_dispatch.h", "_to_sparse_csr_native.h", "unsafe_split_with_sizes.h", "dist.h", "arange_ops.h", "distance.h", "_native_batch_norm_legit_native.h", "floating_point_utils.h", "sinh_meta.h", "fake_quantize_per_channel_affine_native.h", "resolve_neg_native.h", "avg_pool1d_native.h", "multi_margin_loss_backward_native.h", "_mps_convolution_transpose_native.h", "roll.h", "loopnest.h", "promote_types_native.h", "uniform_native.h", "resolve_neg_ops.h", "_new_zeros_with_same_feature_meta_ops.h", "convert_parameters.h", "_fake_quantize_per_tensor_affine_cachemask_tensor_qparams.h", "cumprod_ops.h", "binary_cross_entropy_with_logits_ops.h", "_nnpack_spatial_convolution_compositeexplicitautograd_dispatch.h", "glu_backward_jvp_native.h", "profiler_python.h", "uniform_cuda_dispatch.h", "index_fill_native.h", "_foreach_reciprocal.h", "padding.h", "to_sparse_csc_ops.h", "empty_strided_native.h", "rand_like.h", "DistributionTemplates.h", "_to_sparse_bsc_cuda_dispatch.h", "softmax.h", "norm_except_dim_native.h", "_nnz.h", "isnan.h", "native_dropout_backward_native.h", "atleast_2d_native.h", "cdist.h", "DeviceArray.h", "replication_pad3d_backward_native.h", "lstm_mps_backward_ops.h", "_fake_quantize_learnable_per_tensor_affine_backward_ops.h", "fft_irfftn_ops.h", "softmax_ops.h", "sparse_csc_tensor_ops.h", "retains_grad.h", "python_anomaly_mode.h", "onnx.h", "avg_pool3d.h", "script_init.h", "softplus_backward_meta.h", "fake_quantize_per_tensor_affine_cachemask.h", "QuantizedOps.h", "log_sigmoid_backward.h", "conv2d.h", "_foreach_sin_ops.h", "_cudnn_rnn_backward_compositeexplicitautograd_dispatch.h", "symbolic_shape_cache.h", "_weight_norm_differentiable_backward.h", "thread_pool.h", "_copy_from_and_resize_ops.h", "quantized_max_pool2d_ops.h", "dropout.h", "gru_cell_ops.h", "mkldnn_linear_native.h", "msort.h", "unsqueeze_copy_native.h", "upsample_linear1d_backward_ops.h", "qembeddingbag_prepack.h", "linalg_lu_solve.h", "ctc_loss_native.h", "conj_physical_native.h", "Distributions.h", "to_dense_backward.h", "fold.h", "_index_put_impl_cpu_dispatch.h", "argwhere.h", "fft_rfftn_native.h", "slice_native.h", "logit_backward_cpu_dispatch.h", "pin_memory_compositeimplicitautograd_dispatch.h", "_empty_per_channel_affine_quantized_ops.h", "_foreach_frac_native.h", "matrix_power_ops.h", "clone_native.h", "_foreach_minimum_native.h", "softmax_compositeimplicitautograd_dispatch.h", "rnn_tanh_ops.h", "eye.h", "select_copy.h", "linalg_cond_compositeimplicitautograd_dispatch.h", "CachedTensorUtils.h", "fft_irfft2_native.h", "empty_quantized.h", "sparse_csr_tensor.h", "trace_ops.h", "adaptive_avg_pool3d_backward.h", "matmul_native.h", "acos.h", "cumsum_cuda_dispatch.h", "linalg_svdvals_native.h", "crow_indices_native.h", "replication_pad3d_ops.h", "conv_depthwise3d.h", "_nested_tensor_size_ops.h", "binomial_compositeexplicitautograd_dispatch.h", "index_put_compositeexplicitautograd_dispatch.h", "_sparse_mm_ops.h", "ThreadLocalDebugInfo.h", "int_repr.h", "_weight_norm_differentiable_backward_native.h", "_foreach_sqrt.h", "special_ndtri.h", "remainder_native.h", "_linalg_solve_ex_meta.h", "mkldnn_linear_backward_weights_ops.h", "isin.h", "type_as_ops.h", "softplus_backward_native.h", "LogAddExp.h", "fmax_meta.h", "sum_compositeimplicitautograd_dispatch.h", "_convolution_mode_compositeimplicitautograd_dispatch.h", "pythoncapi_compat.h", "linalg_svd.h", "special_chebyshev_polynomial_w_meta.h", "values_copy.h", "ones_compositeexplicitautograd_dispatch.h", "fft_ifft_ops.h", "_conv_depthwise2d_native.h", "script_type_parser.h", "slogdet_native.h", "_nested_sum_backward_ops.h", "transformercoder.h", "_copy_from_and_resize.h", "ir_views.h", "to_sparse_bsc.h", "_segment_reduce_backward_ops.h", "slow_conv3d.h", "native_layer_norm_backward_cpu_dispatch.h", "_weight_norm_interface_ops.h", "compilation_unit.h", "native_batch_norm_backward_ops.h", "rrelu_with_noise_cpu_dispatch.h", "vec512_complex_float.h", "unflatten_ops.h", "max_pool3d_ops.h", "upsample_nearest2d_backward_cuda_dispatch.h", "linalg_ldl_factor_ex_native.h", "atan_native.h", "new_full_native.h", "ScalarType.h", "_thnn_differentiable_gru_cell_backward_native.h", "CUDAMiscFunctions.h", "argmin_meta_dispatch.h", "gelu_backward_native.h", "fft_fft.h", "log_sigmoid_ops.h", "prod_cpu_dispatch.h", "broadcast_to_ops.h", "_cast_Byte_native.h", "_addmm_activation_meta.h", "matrix_exp_native.h", "diagonal_scatter.h", "_fused_sdp_choice_cpu_dispatch.h", "kl_div_ops.h", "moduledict.h", "tensor_memoryformats.h", "_upsample_nearest_exact3d_meta_dispatch.h", "cudnn_convolution_ops.h", "mkldnn_reorder_conv2d_weight_compositeexplicitautograd_dispatch.h", "frame.h", "align_tensors_ops.h", "special_laguerre_polynomial_l_native.h", "cov.h", "stl.h", "rsub_native.h", "special_i1_meta.h", "type_name_uniquer.h", "TensorGeometry.h", "one_hot.h", "_upsample_nearest_exact1d_ops.h", "special_log1p_native.h", "_masked_softmax_backward_native.h", "reflection_pad1d.h", "trace_backward.h", "mish_ops.h", "segment_reduce_cuda_dispatch.h", "norm.h", "slow_conv_transpose2d_meta_dispatch.h", "UpSample.h", "linalg_matrix_exp_ops.h", "fake_quantize_per_tensor_affine_cachemask_backward_native.h", "argmax_compositeexplicitautogradnonfunctional_dispatch.h", "BFloat16-math.h", "_add_batch_dim_ops.h", "clog.h", "_foreach_sin.h", "clone.h", "clamp_max.h", "unique_dim_consecutive.h", "vararg_functions.h", "_foreach_clamp_min.h", "miopen_batch_norm_backward_native.h", "mkldnn_linear_compositeexplicitautograd_dispatch.h", "elu.h", "cholesky_inverse_ops.h", "mkldnn_reorder_conv3d_weight_ops.h", "fmax.h", "arctan2_ops.h", "cudnn_convolution_relu_ops.h", "multilabel_margin_loss_backward_ops.h", "max_pool2d_backward.h", "sqrt.h", "jiterator_impl.h", "schema_type_parser.h", "unfold_backward_ops.h", "leaky_relu_backward_ops.h", "ccol_indices.h", "view_native.h", "MPSProfiler.h", "upsample_bicubic2d_backward.h", "maximum_meta.h", "slow_conv3d_forward.h", "python_arg_parser.h", "frobenius_norm_ops.h", "to_dense_backward_ops.h", "pooling.h", "max_pool1d_ops.h", "reflection_pad3d_backward_meta.h", "special_multigammaln_native.h", "bitwise_xor.h", "hardsigmoid_native.h", "col_indices.h", "_validate_sparse_compressed_tensor_args_native.h", "std_mean_cuda_dispatch.h", "_embedding_bag_ops.h", "_mps_convolution_transpose.h", "Descriptors.h", "_test_optional_floatlist_compositeexplicitautograd_dispatch.h", "_cudnn_init_dropout_state_native.h", "special_logsumexp.h", "as_strided.h", "contiguous_compositeimplicitautograd_dispatch.h", "_weight_norm_interface_backward_native.h", "upgrader_mobile.h", "peephole_non_tensor.h", "batch_norm_update_stats_cuda_dispatch.h", "cos.h", "op_registration.h", "_cslt_sparse_mm_cuda_dispatch.h", "upsample_bicubic2d_cuda_dispatch.h", "qr_ops.h", "logaddexp2_ops.h", "method.h", "complex.h", "is_pinned_compositeexplicitautograd_dispatch.h", "VariableType.h", "adjoint.h", "pad_compositeimplicitautograd_dispatch.h", "_compute_linear_combination_native.h", "conv3d_ops.h", "descr.h", "EmptyTensor.h", "bernoulli_cpu_dispatch.h", "_thnn_fused_gru_cell_compositeexplicitautograd_dispatch.h", "ge_native.h", "topk_meta.h", "anomaly_mode.h", "avg_pool2d_backward.h", "_test_serialization_subcmul_ops.h", "max_pool2d_with_indices_ops.h", "dynamic_ir.h", "safe_numerics.h", "special_modified_bessel_i1_native.h", "quantized_max_pool3d_native.h", "_sparse_compressed_tensor_unsafe_native.h", "special_bessel_y1_ops.h", "python_legacy_variable.h", "_lstm_mps_ops.h", "special_airy_ai_native.h", "QuantUtils.h", "_nested_select_backward.h", "conj_native.h", "_foreach_addcmul_native.h", "special_log_softmax_compositeimplicitautograd_dispatch.h", "range_compositeexplicitautograd_dispatch.h", "special_airy_ai_ops.h", "CUDAStream.h", "corrcoef_native.h", "LinearAlgebraUtils.h", "arctanh_ops.h", "is_inference_native.h", "glu_backward_ops.h", "not_equal.h", "_cudnn_rnn_ops.h", "parse_bytecode.h", "upsample_nearest2d_backward_ops.h", "adaptive_max_pool2d.h", "group_norm_compositeimplicitautograd_dispatch.h", "fft_ifftn_compositeimplicitautograd_dispatch.h", "_fused_dropout_ops.h", "arange_compositeexplicitautograd_dispatch.h", "_choose_qparams_per_tensor_native.h", "_foreach_log_ops.h", "CUDADataType.h", "import_export_helpers.h", "_cdist_forward_cuda_dispatch.h", "nansum_cpu_dispatch.h", "_pin_memory_native.h", "adaptive_max_pool1d_native.h", "ir_visitor.h", "embedding.h", "logical_and_ops.h", "scatter_ops.h", "is_inference_ops.h", "msort_ops.h", "_sparse_csr_prod_ops.h", "_upsample_bilinear2d_aa_meta.h", "adaption.h", "cosine_similarity_ops.h", "triangular_solve_ops.h", "unique_dim_native.h", "numa.h", "_foreach_clamp_min_ops.h", "arg.h", "_softmax_backward_data_ops.h", "batch_norm_gather_stats_with_counts_ops.h", "dedup_module_uses.h", "replication_pad1d_meta.h", "put_native.h", "digamma_ops.h", "is_nonzero_native.h", "split_with_sizes.h", "erf_ops.h", "convolution_overrideable_ops.h", "gelu_ops.h", "select_scatter_ops.h", "sgn_meta.h", "cumprod_meta.h", "square_ops.h", "_foreach_expm1_native.h", "Functions.h", "i0.h", "repeat_interleave_ops.h", "flip.h", "_debug_has_internal_overlap_ops.h", "tan_ops.h", "isin_native.h", "StorageImpl.h", "frexp_ops.h", "rsqrt.h", "activation.h", "angle_native.h", "special_multigammaln.h", "vec_base.h", "_foreach_frac_ops.h", "multilabel_margin_loss_forward_ops.h", "_ctc_loss.h", "_pack_padded_sequence_backward_native.h", "tril_indices_ops.h", "upsample_trilinear3d_meta_dispatch.h", "sigmoid_meta.h", "max_pool2d_with_indices_backward_ops.h", "jit.h", "layer_norm_native.h", "log_ops.h", "fused_moving_avg_obs_fake_quant_native.h", "_foreach_reciprocal_native.h", "avg_pool3d_native.h", "unique.h", "histc_ops.h", "linalg_solve_triangular_ops.h", "linalg_eig_native.h", "data_parallel.h", "special_shifted_chebyshev_polynomial_w_ops.h", "allclose_ops.h", "ldexp.h", "is_coalesced_native.h", "nll_loss_nd_ops.h", "_validate_sparse_coo_tensor_args.h", "tensor_qschemes.h", "TorchDispatchModeTLS.h", "normalize_ops.h", "upsample_trilinear3d_compositeexplicitautogradnonfunctional_dispatch.h", "_spdiags.h", "Functions.h", "view_as_complex.h", "new_zeros_compositeexplicitautograd_dispatch.h", "_upsample_bicubic2d_aa_compositeimplicitautograd_dispatch.h", "fmin_meta.h", "peephole_alias_sensitive.h", "softshrink_native.h", "special_erf_native.h", "sum_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_trilinear3d_backward_meta_dispatch.h", "upsample_trilinear3d_ops.h", "dtype_analysis.h", "_triton_multi_head_attention_native.h", "ThreadLocalPythonObjects.h", "randn.h", "lstm_cell_native.h", "hardshrink_backward_ops.h", "Layout.h", "orgqr_ops.h", "cumulative_trapezoid.h", "_prelu_kernel_backward.h", "max_pool2d_backward_native.h", "cpp_intrinsics.h", "rnn_tanh_cell_ops.h", "_foreach_round.h", "max_pool3d_with_indices_backward.h", "pimpl.h", "erfc_ops.h", "addr.h", "max.h", "sqrt_ops.h", "strong_type.h", "to_mkldnn_backward_ops.h", "bernoulli.h", "rot90_native.h", "symbolic_script.h", "python_ivalue.h", "moveaxis_native.h", "upsample_linear1d_backward_cpu_dispatch.h", "rnn.h", "utils.h", "flip_ops.h", "python_fft_functions.h", "linalg_matrix_exp.h", "_functional_sym_constrain_range_compositeexplicitautograd_dispatch.h", "Pow.h", "lu_unpack_ops.h", "crow_indices.h", "_nested_view_from_buffer_copy.h", "renorm_native.h", "tanh_backward_meta.h", "_addmm_activation.h", "_fused_dropout_native.h", "logit_backward_compositeexplicitautogradnonfunctional_dispatch.h", "fwd_decls.h", "relu6.h", "_prelu_kernel_native.h", "Macros.h", "as_strided_copy_native.h", "std_mean_ops.h", "geometric_cuda_dispatch.h", "huber_loss.h", "structseq.h", "_sparse_csr_prod_native.h", "_sparse_sparse_matmul_ops.h", "MPSGuardImpl.h", "_upsample_bicubic2d_aa_cuda_dispatch.h", "masked_select.h", "special_shifted_chebyshev_polynomial_v_meta.h", "is_set_to.h", "glu_backward_jvp_ops.h", "is_leaf_native.h", "special_logit_compositeimplicitautograd_dispatch.h", "lift_closures.h", "fft_fft2.h", "randperm_cpu_dispatch.h", "List.h", "mkldnn_reorder_conv2d_weight.h", "gt_ops.h", "quantized_max_pool2d.h", "glu.h", "var_mean_cuda_dispatch.h", "mv_native.h", "view_as_real.h", "sigmoid_backward_meta.h", "linalg_svdvals_ops.h", "pixel_unshuffle_native.h", "einsum_native.h", "upsample_nearest1d_backward_native.h", "DynamicLayer.h", "aminmax_meta_dispatch.h", "step_lr.h", "special_psi_ops.h", "log_softmax_ops.h", "_copy_from.h", "RedispatchFunctions.h", "nll_loss_forward_meta.h", "bitwise_or_meta.h", "ts_node_lowering.h", "cumulative_trapezoid_ops.h", "graph_fuser.h", "as_strided_copy.h", "conv3d_compositeimplicitautograd_dispatch.h", "record_function.h", "le_meta.h", "SpmmReduceKernel.h", "_nested_tensor_strides_native.h", "masked_select_native.h", "inductor_ops.h", "bitwise_not_meta.h", "values.h", "cpp_hook.h", "PyHandleCache.h", "_test_check_tensor.h", "gcd.h", "linear_compositeimplicitautograd_dispatch.h", "_functional_assert_async.h", "linalg_cholesky_ex.h", "special_bessel_y1_meta.h", "retain_grad.h", "chalf_native.h", "linalg_matrix_norm.h", "check_strict_fusion.h", "deg2rad_native.h", "hann_window_compositeexplicitautograd_dispatch.h", "_conv_depthwise2d.h", "_to_sparse_native.h", "special_exp2_ops.h", "upsample_nearest3d_cuda_dispatch.h", "copysign.h", "scatter.h", "to_sparse_csr_native.h", "native_dropout_cpu_dispatch.h", "greater.h", "MPSAllocatorInterface.h", "random_meta_dispatch.h", "_weight_norm_interface_native.h", "unfold_ops.h", "add_meta.h", "_fft_c2c_ops.h", "binary_cross_entropy_ops.h", "Event.h", "request_callback_impl.h", "type_caster_base.h", "log_softmax_compositeimplicitautograd_dispatch.h", "sparse_sampled_addmm.h", "_pdist_forward_native.h", "unfold_native.h", "diagflat.h", "record_function_ops.h", "mkldnn_max_pool3d.h", "cumsum_cpu_dispatch.h", "put.h", "bitwise_left_shift_meta.h", "linalg_lu_factor_ops.h", "isclose_native.h", "randperm.h", "TypeIndex.h", "Context.h", "python_arg_flatten.h", "bincount_cuda_dispatch.h", "exp2_ops.h", "i0_meta.h", "linear.h", "_to_sparse_bsr_ops.h", "_pin_memory_compositeexplicitautograd_dispatch.h", "hardtanh_ops.h", "fft_fftn_native.h", "SymNodeImpl.h", "python_functions.h", "_embedding_bag.h", "_remove_batch_dim_native.h", "unpickler.h", "_to_sparse_csr_ops.h", "avg_pool2d_meta_dispatch.h", "_efficient_attention_forward_cuda_dispatch.h", "any_value.h", "native_layer_norm_cpu_dispatch.h", "CUDAHooks.h", "utils.h", "fake_quantize_per_channel_affine.h", "vec.h", "as_strided_scatter_ops.h", "upsample_nearest1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "kernel.h", "randn_like_compositeimplicitautogradnestedtensor_dispatch.h", "det_ops.h", "feature_dropout_ops.h", "cholesky_solve_ops.h", "avg_pool3d_backward_meta_dispatch.h", "full_like_compositeexplicitautograd_dispatch.h", "accumulate_grad.h", "_unpack_dual_ops.h", "tensorpipe_utils.h", "linalg_vector_norm_meta.h", "leaky_relu.h", "glu_ops.h", "special_shifted_chebyshev_polynomial_w_meta.h", "cosh_meta.h", "arctan.h", "miopen_depthwise_convolution_ops.h", "pybind11.h", "isclose_ops.h", "irparser.h", "relu6_ops.h", "select_backward_native.h", "random_compositeexplicitautograd_dispatch.h", "to_native.h", "native_batch_norm_ops.h", "mkldnn_max_pool3d_backward_ops.h", "memory_dag.h", "neg_native.h", "vec512_double.h", "ones_native.h", "_transformer_encoder_layer_fwd_ops.h", "mkldnn_reorder_conv3d_weight_native.h", "embedding_bag.h", "sparse_csc_tensor_native.h", "_conj_native.h", "ir.h", "_thnn_fused_lstm_cell_backward_impl_ops.h", "conv_depthwise3d_native.h", "threshold_backward_native.h", "cudnn_convolution_add_relu_compositeexplicitautograd_dispatch.h", "cudnn_affine_grid_generator_backward.h", "bilinear_compositeimplicitautograd_dispatch.h", "IsContiguous.h", "_transform_bias_rescale_qkv.h", "_foreach_atan_native.h", "dequantize.h", "_upsample_bicubic2d_aa_backward.h", "_embedding_bag_native.h", "map.h", "_thnn_differentiable_gru_cell_backward_compositeimplicitautograd_dispatch.h", "is_conj_native.h", "reflection_pad3d_ops.h", "_shape_as_tensor_ops.h", "special_chebyshev_polynomial_u.h", "frac_meta.h", "requires_grad_ops.h", "logspace_compositeexplicitautograd_dispatch.h", "_thnn_fused_lstm_cell_backward_ops.h", "moments_utils.h", "_foreach_add_ops.h", "index_meta_dispatch.h", "_sample_dirichlet_cpu_dispatch.h", "special_laguerre_polynomial_l.h", "adaptive_max_pool3d_meta.h", "mode_native.h", "ts_eager_fallback.h", "_linalg_det_ops.h", "cleanup_autograd_context_resp.h", "fractional_max_pool2d_native.h", "_linalg_eigh.h", "tan_meta.h", "log1p_meta.h", "BatchRulesHelper.h", "is_pinned.h", "mkldnn_max_pool3d_backward_native.h", "upsample_nearest1d_compositeimplicitautograd_dispatch.h", "special_chebyshev_polynomial_t_ops.h", "sub_ops.h", "_flash_attention_forward_native.h", "bailout_graph.h", "trapezoid_ops.h", "gather_backward.h", "pixelshuffle.h", "log2_meta.h", "vec256_qint8_vsx.h", "autograd_metadata.h", "empty_strided.h", "_upsample_bicubic2d_aa_cpu_dispatch.h", "HIPHooksInterface.h", "sym_constrain_range.h", "quantize_per_channel_native.h", "nll_loss_backward_compositeexplicitautogradnonfunctional_dispatch.h", "_convolution.h", "tree_views.h", "q_scale_ops.h", "_functional_sym_constrain_range.h", "_softmax_backward_data_native.h", "floor_meta.h", "mean_native.h", "rename.h", "upsample_linear1d_backward.h", "mkldnn_linear_backward_native.h", "fft_fftshift_native.h", "ne_ops.h", "_to_sparse_semi_structured_ops.h", "graph_opt.h", "prod_cuda_dispatch.h", "isnan_native.h", "special_chebyshev_polynomial_u_native.h", "grid_sampler_2d_backward_native.h", "upsample_nearest1d_backward_meta.h", "CPUApplyUtils.h", "ScalarTypeToTypeMeta.h", "isneginf_ops.h", "histogramdd.h", "dataloader_options.h", "SymBool.h", "_coalesced_native.h", "activation.h", "upsampling.h", "_upsample_nearest_exact1d_compositeexplicitautogradnonfunctional_dispatch.h", "slow_conv3d_forward_ops.h", "ccol_indices_copy_ops.h", "nextafter_native.h", "_pin_memory.h", "poisson_compositeexplicitautograd_dispatch.h", "CheckMemoryFormat.h", "linalg_slogdet_native.h", "masked_select_backward_ops.h", "conv1d.h", "fft_fftshift_compositeimplicitautograd_dispatch.h", "special_gammainc_ops.h", "_sobol_engine_draw_ops.h", "roll_ops.h", "layer_norm.h", "_conj_copy.h", "empty_like_native.h", "fbgemm_linear_fp16_weight_fp32_activation_ops.h", "linalg_vector_norm_native.h", "to_sparse_bsc_native.h", "indices_ops.h", "stride.h", "sum_meta.h", "batch_norm_update_stats_compositeexplicitautograd_dispatch.h", "view_as_complex_native.h", "le_ops.h", "_upsample_bilinear2d_aa_backward_ops.h", "upsample_nearest1d_ops.h", "adaptive_avg_pool1d_ops.h", "add.h", "slow_conv_transpose2d_cpu_dispatch.h", "unique_name_manager.h", "input_metadata.h", "special_modified_bessel_k1.h", "_upsample_nearest_exact1d_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_w_native.h", "prod_native.h", "script_call.h", "cosine_similarity_native.h", "_fused_adam_native.h", "_linalg_solve_ex_native.h", "Array.h", "bitwise_or_ops.h", "_foreach_log10_native.h", "_empty_per_channel_affine_quantized_compositeexplicitautograd_dispatch.h", "atleast_3d_ops.h", "EmbeddingPackedParams.h", "_foreach_trunc_native.h", "unflatten.h", "im2col_native.h", "view_ops.h", "randn_like_native.h", "_cufft_get_plan_cache_size_ops.h", "q_per_channel_zero_points.h", "reshape_as_native.h", "GeneratorImpl.h", "mps_convolution_transpose_backward_ops.h", "QScheme.h", "replacement_of_old_operators.h", "clamp_meta_dispatch.h", "_log_softmax_ops.h", "_foreach_zero_native.h", "pad_sequence.h", "collection.h", "item_ops.h", "socket.h", "_fake_quantize_learnable_per_channel_affine_ops.h", "type_as_native.h", "_make_dep_token.h", "special_zeta.h", "remove_inplace_ops.h", "mkldnn_rnn_layer_backward_compositeexplicitautograd_dispatch.h", "cummax.h", "operator.h", "python_linalg_functions.h", "_stack_native.h", "PyObjectSlot.h", "_foreach_sqrt_ops.h", "empty_ops.h", "miopen_batch_norm_cuda_dispatch.h", "miopen_convolution_transpose_cuda_dispatch.h", "back_compat.h", "select_scatter.h", "mkldnn_adaptive_avg_pool2d.h", "special_bessel_y0_native.h", "eliminate_no_ops.h", "MPSDevice.h", "_test_check_tensor_native.h", "vec512_complex_double.h", "hardshrink_ops.h", "exponential.h", "_ctc_loss_backward_ops.h", "special_logsumexp_native.h", "avg_pool2d_backward_meta_dispatch.h", "matmul.h", "rpc_with_autograd.h", "_cdist_forward_cpu_dispatch.h", "special_scaled_modified_bessel_k0.h", "_mps_convolution_transpose_ops.h", "new_full.h", "fmin_ops.h", "std_native.h", "cat_native.h", "embedding.h", "tensordot_ops.h", "mini_environment.h", "batch_norm_backward_reduce_ops.h", "rnn_tanh_cell.h", "_functions.h", "subgraph_utils.h", "_sparse_bsc_tensor_unsafe.h", "minimum_meta.h", "sparse_mask.h", "_to_cpu_ops.h", "nll_loss_backward.h", "sparse_bsc_tensor_compositeimplicitautograd_dispatch.h", "nanquantile_compositeimplicitautograd_dispatch.h", "promote_types_ops.h", "base.h", "convert_to_ssa.h", "argmax_ops.h", "mkldnn_linear_backward_input_ops.h", "_upsample_bilinear2d_aa_backward_cpu_dispatch.h", "take_along_dim_compositeimplicitautograd_dispatch.h", "native_group_norm_backward_cuda_dispatch.h", "polar_ops.h", "sparse_dim_ops.h", "common.h", "external_functions.h", "LocalDispatchKeySet.h", "CatKernel.h", "adaptive_max_pool2d_native.h", "arcsin_ops.h", "special_i1.h", "vec512.h", "hardswish_backward_native.h", "restore_mutation.h", "print_handler.h", "grid_sampler_3d_ops.h", "upsample_nearest2d.h", "_cufft_get_plan_cache_max_size.h", "batch_norm_stats_native.h", "avg_pool3d_backward_meta.h", "nan_to_num.h", "as_strided_copy_compositeexplicitautograd_dispatch.h", "ge_meta.h", "pooling.h", "fold_conv_bn.h", "geqrf_ops.h", "reflection_pad1d_meta.h", "_has_same_storage_numel_ops.h", "fft_ifft2_compositeimplicitautograd_dispatch.h", "_remove_batch_dim.h", "_foreach_sign_native.h", "polar.h", "nll_loss2d_native.h", "ThreadLocalState.h", "special_expit.h", "rnn_tanh_native.h", "_aminmax_ops.h", "_transformer_encoder_layer_fwd.h", "slow_conv_dilated3d_ops.h", "_sparse_csc_tensor_unsafe_compositeimplicitautograd_dispatch.h", "_transformer_encoder_layer_fwd_cuda_dispatch.h", "slow_conv_transpose3d_ops.h", "_local_scalar_dense_ops.h", "special_hermite_polynomial_he_native.h", "special_erfinv_native.h", "init.h", "special_expm1_ops.h", "resize_as.h", "isneginf_meta.h", "sparse_resize_and_clear_ops.h", "linalg_diagonal_ops.h", "leaky_relu_ops.h", "embedding_renorm_native.h", "special_erfc_ops.h", "profiler_edge.h", "_efficientzerotensor_ops.h", "nll_loss2d_ops.h", "_thnn_differentiable_lstm_cell_backward.h", "SafePyObject.h", "native_batch_norm_backward_cuda_dispatch.h", "_transformer_encoder_layer_fwd_native.h", "rnn_tanh_cell_compositeimplicitautograd_dispatch.h", "fft_rfftn.h", "upsample_bicubic2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "MaxPooling.h", "atleast_3d.h", "_masked_softmax_backward_compositeexplicitautograd_dispatch.h", "logical_xor_native.h", "native_layer_norm_cuda_dispatch.h", "randperm_compositeexplicitautograd_dispatch.h", "_sparse_csc_tensor_unsafe_ops.h", "MaxUnpoolKernel.h", "replication_pad2d_meta.h", "to_dense.h", "reflection_pad2d_backward.h", "mkldnn_max_pool2d_native.h", "fft_ifftshift_native.h", "edge.h", "special_chebyshev_polynomial_v.h", "kaiser_window.h", "select_ops.h", "fft_fftfreq_native.h", "native_layer_norm_backward_native.h", "_upsample_nearest_exact1d_backward.h", "cosh_native.h", "randperm_native.h", "atleast_1d_ops.h", "_nested_from_padded_native.h", "SymFloat.h", "narrow_native.h", "linalg_matrix_norm_compositeimplicitautograd_dispatch.h", "ParallelNative.h", "replication_pad1d_native.h", "conv_transpose1d_compositeimplicitautograd_dispatch.h", "special_erf.h", "matrix_exp_backward_native.h", "_softmax_backward_data.h", "moveaxis.h", "_standard_gamma_native.h", "special_expm1.h", "linalg_vecdot_ops.h", "_sobol_engine_draw.h", "_masked_softmax_backward_ops.h", "_foreach_expm1_ops.h", "Utils.h", "aminmax_meta.h", "bitwise_not_native.h", "Float8_e4m3fn-inl.h", "fft_hfftn_ops.h", "avg_pool2d_native.h", "avg_pool2d_cpu_dispatch.h", "arange.h", "choose_qparams_optimized.h", "upsample_nearest1d_backward_cpu_dispatch.h", "loop_unrolling.h", "_to_sparse_cpu_dispatch.h", "soft_margin_loss_backward_native.h", "_sparse_sum_native.h", "_reshape_alias_ops.h", "Vitals.h", "repeat_interleave_compositeexplicitautograd_dispatch.h", "_nested_view_from_buffer.h", "linalg_pinv.h", "erf.h", "xor_ops.h", "to_ops.h", "exp2_native.h", "tril_indices_cuda_dispatch.h", "addcmul.h", "det.h", "fft_ihfft2.h", "Dtype.h", "_foreach_norm_cuda_dispatch.h", "mkldnn_max_pool3d_ops.h", "unique_consecutive_cpu_dispatch.h", "ir_mutator.h", "upsample_bicubic2d_backward_cuda_dispatch.h", "fft_hfftn_compositeimplicitautograd_dispatch.h", "_slow_conv2d_backward_ops.h", "vstack.h", "jit_trace.h", "_foreach_lgamma_ops.h", "resolve_conj.h", "binomial_cpu_dispatch.h", "replication_pad3d_backward_ops.h", "mkldnn_reorder_conv2d_weight_ops.h", "python_list.h", "Exceptions.h", "TensorOperators.h", "special_spherical_bessel_j0_meta.h", "_upsample_nearest_exact1d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "var_cuda_dispatch.h", "ir_builder.h", "stft_compositeimplicitautograd_dispatch.h", "slice_ops.h", "eval_frame.h", "miopen_convolution_transpose_ops.h", "native_group_norm_ops.h", "python_torch_function_mode.h", "cudnn_convolution.h", "clamp_ops.h", "unique_dim_consecutive_ops.h", "graph_task.h", "_nested_tensor_softmax_with_shape.h", "q_scale_native.h", "eye_native.h", "values_ops.h", "mish_meta.h", "softmax_native.h", "linalg_pinv_native.h", "_pack_padded_sequence_native.h", "rrelu.h", "upsample_linear1d_native.h", "special_chebyshev_polynomial_v_meta.h", "slice_backward_native.h", "_propagate_xla_data_ops.h", "vec256_quint8_vsx.h", "batch_norm_gather_stats.h", "norm_cpu_dispatch.h", "native_layer_norm_native.h", "linalg_matmul_native.h", "special_scaled_modified_bessel_k1.h", "module_python.h", "flatten_dense_tensors_native.h", "decomposition_registry.h", "import_read.h", "init_qnnpack.h", "dead_code_elimination.h", "upsample_nearest3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_solve_ex_native.h", "_convert_indices_from_csr_to_coo_native.h", "new_full_ops.h", "_cudnn_rnn_cuda_dispatch.h", "linalg_svdvals.h", "cumprod_native.h", "amax_meta.h", "special_log_softmax_ops.h", "hardshrink_backward_native.h", "_pdist_forward.h", "logit_backward_ops.h", "flipud.h", "sparse_compressed_tensor_compositeexplicitautograd_dispatch.h", "_compute_linear_combination_ops.h", "gcd_ops.h", "cross_entropy_loss_native.h", "special_shifted_chebyshev_polynomial_t_native.h", "copy_sparse_to_sparse.h", "empty_native.h", "bitwise_not_ops.h", "mm_meta.h", "_has_compatible_shallow_copy_type.h", "copy.h", "cauchy_meta_dispatch.h", "sinc_native.h", "special_gammaincc.h", "eq.h", "_foreach_addcdiv.h", "index_select_backward.h", "triu_indices_ops.h", "optimization_utils.h", "_sparse_csr_tensor_unsafe_ops.h", "_has_same_storage_numel.h", "topk_native.h", "_upsample_bicubic2d_aa.h", "clamp_min_native.h", "dist_ops.h", "sort_compositeexplicitautogradnonfunctional_dispatch.h", "batch_norm_backward_elemt_compositeexplicitautograd_dispatch.h", "chain_matmul_ops.h", "jit_type.h", "Allocator.h", "WrapDimUtils.h", "asin_meta.h", "_cast_Byte_ops.h", "_foreach_sub_ops.h", "to_sparse_csr.h", "normal_cuda_dispatch.h", "matrix_H_native.h", "StreamGuard.h", "var_native.h", "view_as.h", "cpp_custom_type_hack.h", "NativeMetaFunction.h", "sparse_bsr_tensor_native.h", "_sparse_sum_backward_native.h", "_thnn_fused_gru_cell_backward_native.h", "_sparse_csc_tensor_unsafe_native.h", "values_native.h", "matrix_H.h", "linalg_lu_solve_native.h", "softplus_backward_ops.h", "special_entr_meta.h", "isposinf_native.h", "_nested_tensor_strides.h", "fake_quantize_per_tensor_affine_cachemask_native.h", "instance_norm.h", "neg_meta.h", "equal_native.h", "_segment_reduce_backward_cpu_dispatch.h", "_ctc_loss_native.h", "operator_options.h", "_fused_sdp_choice_cuda_dispatch.h", "resize_cpu_dispatch.h", "random_cuda_dispatch.h", "_triton_scaled_dot_attention_native.h", "im2col_shape_check.h", "cudnn_convolution_add_relu_native.h", "special_log_softmax_native.h", "op_registry.h", "new_empty_strided_compositeexplicitautogradnonfunctional_dispatch.h", "int128.h", "transformercoder.h", "cumsum_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_compressed_tensor_unsafe_compositeimplicitautograd_dispatch.h", "unsqueeze_copy_ops.h", "masked_fill_native.h", "ExpandUtils.h", "asinh_ops.h", "avg_pool3d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "reciprocal_meta.h", "order_preserving_flat_hash_map.h", "_empty_per_channel_affine_quantized_cpu_dispatch.h", "_sparse_addmm_ops.h", "OperatorKernel.h", "_foreach_clamp_max.h", "multilabel_margin_loss_ops.h", "_foreach_neg_native.h", "native_layer_norm_ops.h", "external_functions_core.h", "upsample_bicubic2d_ops.h", "unfold_copy.h", "backend_resolver.h", "unique_consecutive_compositeexplicitautograd_dispatch.h", "huber_loss_native.h", "feature_alpha_dropout_native.h", "threshold_backward_ops.h", "quantized_rnn_relu_cell_native.h", "_reshape_alias_native.h", "cudnn_is_acceptable_native.h", "mps_convolution_backward_native.h", "_empty_affine_quantized.h", "leaky_relu_native.h", "fmin.h", "multi_margin_loss_backward_ops.h", "split_copy_native.h", "celu_ops.h", "absolute_ops.h", "cross_entropy_loss.h", "sigmoid_backward.h", "tanh.h", "python.h", "env.h", "_thnn_fused_gru_cell_cuda_dispatch.h", "upsample_linear1d_cuda_dispatch.h", "align_as_ops.h", "detach_copy_native.h", "_cummax_helper.h", "_upsample_bilinear2d_aa_backward_compositeexplicitautogradnonfunctional_dispatch.h", "batch_mm.h", "_fft_r2c.h", "nuclear_norm.h", "bincount_cpu_dispatch.h", "as_strided_cuda_dispatch.h", "threshold_ops.h", "linalg_diagonal_native.h", "_embedding_bag_backward_ops.h", "native_batch_norm.h", "pairwise_distance_native.h", "record_stream_native.h", "_histogramdd_bin_edges_compositeexplicitautograd_dispatch.h", "_backward_native.h", "insert_observers.h", "linalg_lu.h", "_native_multi_head_attention_cpu_dispatch.h", "_has_compatible_shallow_copy_type_native.h", "quantization_patterns.h", "addr_ops.h", "resize_ops.h", "CUDAGraphsC10Utils.h", "_validate_sparse_coo_tensor_args_native.h", "_validate_sparse_csc_tensor_args_native.h", "_slow_conv2d_forward_cuda_dispatch.h", "_sparse_coo_tensor_with_dims.h", "nll_loss_backward_cuda_dispatch.h", "random_ops.h", "backend_data.h", "new_ones_native.h", "max_unpool2d_native.h", "external_functions_registry.h", "bounds_inference.h", "_foreach_clamp_min_native.h", "_thnn_fused_lstm_cell_backward_compositeimplicitautograd_dispatch.h", "_efficientzerotensor_meta_dispatch.h", "_new_zeros_with_same_feature_meta_native.h", "_test_optional_intlist_native.h", "linalg_solve_triangular_native.h", "_thnn_differentiable_lstm_cell_backward_native.h", "_linalg_solve_ex.h", "acos_ops.h", "mkldnn_linear_ops.h", "cat_ops.h", "var_mean.h", "alias_analysis.h", "python_tracer.h", "_foreach_norm_native.h", "fake_quantize_per_channel_affine_ops.h", "_softmax_ops.h", "_autocast_to_reduced_precision_native.h", "softshrink_backward_native.h", "_adaptive_avg_pool3d_backward_ops.h", "row_stack_ops.h", "_make_dep_token_native.h", "_foreach_cos.h", "addbmm.h", "_reshape_copy_ops.h", "data_flow.h", "exceptions.h", "bernoulli_native.h", "_segment_reduce_backward_compositeexplicitautograd_dispatch.h", "_unique2_ops.h", "fft_hfftn_native.h", "affine_grid_generator_native.h", "ir_printer.h", "hardswish_native.h", "_fused_adamw_cuda_dispatch.h", "arithmetic_ir_ops.h", "vec512_qint.h", "TorchDispatchUtils.h", "special_gammaincc_native.h", "_gather_sparse_backward_native.h", "miopen_batch_norm_ops.h", "slow_conv_dilated3d_cpu_dispatch.h", "alias_copy_native.h", "greater_ops.h", "_efficient_attention_forward.h", "take_ops.h", "linear_native.h", "rnn_tanh_cell_native.h", "_fused_adamw_ops.h", "special_shifted_chebyshev_polynomial_t_meta.h", "_thnn_fused_gru_cell_ops.h", "_pack_padded_sequence_ops.h", "_unsafe_index.h", "log1p_native.h", "_functional_assert_async_native.h", "special_ndtri_meta.h", "onnx.h", "_logcumsumexp_native.h", "clear_profiling.h", "_dimI_native.h", "hypot_meta.h", "var_substitutor.h", "fake_quantize_per_tensor_affine_cachemask_ops.h", "instance_norm_ops.h", "_embedding_bag_forward_only.h", "mvlgamma.h", "std_mean_native.h", "native_group_norm_backward_ops.h", "concrete_module_type.h", "native_layer_norm_backward_cuda_dispatch.h", "_batch_norm_impl_index_backward_compositeimplicitautograd_dispatch.h", "logaddexp_meta.h", "rand_native.h", "dropout.h", "upsample_nearest1d_meta.h", "lift_fresh_native.h", "adaptive_avg_pool2d_native.h", "inline_container.h", "import_export_constants.h", "_fused_sdp_choice_meta_dispatch.h", "_test_autograd_multiple_dispatch_view_copy_native.h", "pybind.h", "_adaptive_avg_pool2d_backward.h", "_mkldnn_transpose.h", "linalg_householder_product_ops.h", "rshift.h", "index_ops.h", "slow_conv_dilated2d.h", "_efficient_attention_backward.h", "cudnn_batch_norm_backward.h", "Bitset.h", "numpy_T_native.h", "python_arg_parsing.h", "decompose_ops.h", "trunc_ops.h", "upsample_bilinear2d_native.h", "accumulate.h", "q_per_channel_axis_native.h", "aminmax.h", "select_native.h", "vulkan_rewrite.h", "native_batch_norm_backward_compositeexplicitautograd_dispatch.h", "_version_native.h", "as_strided_cpu_dispatch.h", "arctan2_native.h", "_coalesce_native.h", "conv.h", "special_i0e_native.h", "fake_quantize_per_channel_affine_cachemask_backward_ops.h", "nonzero_numpy_native.h", "slow_conv_dilated2d_compositeexplicitautograd_dispatch.h", "quantized_rnn_relu_cell_ops.h", "special_exp2.h", "special_bessel_y1_native.h", "VariableType.h", "ir_util.h", "_sparse_log_softmax_backward_data_ops.h", "tensor_split_ops.h", "ctc_loss.h", "miopen_convolution_add_relu_ops.h", "_convert_indices_from_coo_to_csr_ops.h", "fft_fftfreq_ops.h", "record_stream.h", "random.h", "_log_softmax_native.h", "multinomial_native.h", "_foreach_sub_native.h", "avg_pool2d.h", "tensor_split_native.h", "native_norm.h", "swapdims_ops.h", "_embedding_bag_per_sample_weights_backward.h", "sum_ops.h", "_foreach_abs.h", "flatbuffer_loader.h", "_masked_scale.h", "_functional_sym_constrain_range_for_size.h", "exp_native.h", "TensorCompare.h", "grid_sampler_3d_native.h", "xnnpack_rewrite.h", "sigmoid_backward_native.h", "tensordot.h", "OperatorOptions.h", "real_ops.h", "bitwise_or.h", "CUDAMathCompat.h", "conv_transpose3d_ops.h", "_pad_enum_ops.h", "backend_interface.h", "cudnn_grid_sampler_ops.h", "_index_put_impl_ops.h", "frozen_graph_optimizations.h", "subtract_native.h", "index_compositeexplicitautogradnonfunctional_dispatch.h", "is_coalesced.h", "sinc_meta.h", "_upsample_nearest_exact2d_backward_meta.h", "_batch_norm_impl_index_ops.h", "tensor_numpy.h", "multi_margin_loss_native.h", "linalg_lu_factor_ex_native.h", "_cast_Float_ops.h", "cuda_codegen.h", "index_meta.h", "SparseCsrTensorImpl.h", "rshift_native.h", "linalg_multi_dot.h", "TensorModeKernel.h", "mvlgamma_native.h", "_test_autograd_multiple_dispatch_view.h", "fft_irfft.h", "prim_ops_registery.h", "_functional_sym_constrain_range_for_size_ops.h", "_autocast_to_reduced_precision_ops.h", "blob.h", "igammac_meta.h", "_scaled_dot_product_flash_attention_backward_ops.h", "batch_norm_elemt_ops.h", "Handle.h", "linalg_householder_product_native.h", "_nested_tensor_size.h", "rpc_with_profiling_resp.h", "fbgemm_pack_quantized_matrix.h", "arcsinh.h", "source_range_serialization_impl.h", "nll_loss2d_forward.h", "greater_native.h", "embedding_dense_backward_native.h", "hardtanh.h", "fft_fftfreq.h", "_upsample_nearest_exact3d_backward_cpu_dispatch.h", "mse_loss_native.h", "slogdet_ops.h", "create_autodiff_subgraphs.h", "_cdist_forward_native.h", "one_hot_ops.h", "linalg_inv_native.h", "_values_copy.h", "clip.h", "lcm_native.h", "index_put.h", "cartesian_prod.h", "soft_margin_loss_native.h", "_foreach_sqrt_native.h", "greater_equal_native.h", "type_ptr.h", "linalg_inv_ops.h", "slice_indices_adjust.h", "pdist.h", "convolution_compositeexplicitautograd_dispatch.h", "_standard_gamma_grad_ops.h", "clip_ops.h", "MemoryFormat.h", "avg_pool3d_backward.h", "min_native.h", "softshrink_backward_ops.h", "gt_meta.h", "python_hook.h", "reflection_pad3d_meta.h", "as_strided_scatter_compositeexplicitautograd_dispatch.h", "bucketize_native.h", "scatter_native.h", "Resize.h", "function.h", "squeeze.h", "conv_transpose1d_native.h", "split_with_sizes_native.h", "elu_ops.h", "replication_pad1d_backward.h", "_foreach_exp_native.h", "diag_native.h", "_triton_multi_head_attention.h", "_thnn_fused_gru_cell_backward_ops.h", "device_set.h", "serialize.h", "_nested_tensor_from_tensor_list_ops.h", "index_add_native.h", "variadic_ops.h", "promote_types.h", "atan2_meta.h", "_sparse_compressed_tensor_unsafe.h", "Formatting.h", "mul.h", "batch_norm_stats.h", "cumsum.h", "index_add_ops.h", "index_cuda_dispatch.h", "searchsorted.h", "atleast_2d_ops.h", "version.h", "softmax_compositeexplicitautograd_dispatch.h", "is_complex.h", "graph_utils.h", "slow_conv_dilated2d_ops.h", "schema_matching.h", "_upsample_nearest_exact1d_backward_cpu_dispatch.h", "to_mkldnn_backward.h", "logcumsumexp_ops.h", "sgn_ops.h", "_make_dual_copy_native.h", "soft_margin_loss_ops.h", "nan_to_num_ops.h", "_test_ambiguous_defaults_native.h", "diagflat_ops.h", "can_cast_native.h", "lu_solve_ops.h", "_upsample_nearest_exact2d_backward_native.h", "isnan_ops.h", "_add_batch_dim.h", "svd_ops.h", "fft_rfftn_compositeimplicitautograd_dispatch.h", "fft_ifftshift_compositeimplicitautograd_dispatch.h", "fft_rfftfreq_native.h", "bitwise_not.h", "corrcoef_ops.h", "sign_native.h", "_unpack_dual_native.h", "as_strided_copy_ops.h", "heaviside.h", "_upsample_nearest_exact2d_backward_meta_dispatch.h", "mps.h", "mean_compositeexplicitautogradnonfunctional_dispatch.h", "upsample_bilinear2d_meta_dispatch.h", "special_erfinv_ops.h", "special_zeta_meta.h", "silu_backward.h", "argsort_ops.h", "std_mean_compositeexplicitautograd_dispatch.h", "cudnn_affine_grid_generator_backward_ops.h", "diagonal_copy_native.h", "_foreach_zero_ops.h", "masked_scatter_native.h", "cudnn_grid_sampler_backward_ops.h", "unsafe_chunk_ops.h", "acos_native.h", "WrapFunctionIntoRuntimeFunctor.h", "nonzero_ops.h", "grid_sampler_2d_backward_ops.h", "_upsample_bilinear2d_aa_backward_meta_dispatch.h", "mkldnn_rnn_layer_backward_ops.h", "upsample_nearest2d_compositeimplicitautograd_dispatch.h", "special_xlogy_native.h", "_cufft_get_plan_cache_size_native.h", "sparse_bsr_tensor_ops.h", "_is_any_true_native.h", "_fft_c2c_native.h", "linalg_vander.h", "cumprod_backward_native.h", "NamedTensor.h", "_scaled_mm_ops.h", "fractional_max_pool2d_meta.h", "special_erfcx.h", "erf_meta.h", "upsample_nearest1d_native.h", "promoted_prim_ops.h", "upsample_linear1d_backward_cuda_dispatch.h", "_convolution_compositeexplicitautograd_dispatch.h", "batchnorm.h", "_is_all_true_native.h", "pow_meta.h", "log1p.h", "slice_scatter_native.h", "subgraph_rewrite.h", "fmod.h", "_autocast_to_full_precision.h", "mkldnn_max_pool3d_native.h", "miopen_batch_norm_backward_cuda_dispatch.h", "sub_meta.h", "embedding_bag_compositeimplicitautograd_dispatch.h", "cast.h", "NativeFunction.h", "loss.h", "native_norm_ops.h", "NestedTensorImpl.h", "zeros_like_compositeimplicitautogradnestedtensor_dispatch.h", "_nested_from_padded_and_nested_example.h", "_foreach_erfc_ops.h", "nll_loss_forward_cuda_dispatch.h", "diff_compositeimplicitautograd_dispatch.h", "_standard_gamma_grad.h", "_adaptive_avg_pool3d.h", "kron_ops.h", "_fft_c2r.h", "qr_native.h", "_dirichlet_grad_ops.h", "asin.h", "_cast_Double.h", "index_reduce_meta.h", "hardshrink_backward_meta.h", "max_pool3d.h", "argmax_meta.h", "_pad_circular_native.h", "pybind_utils.h", "lstm_mps_backward_native.h", "reflection_pad3d_backward_native.h", "empty_like.h", "stft_native.h", "mT_ops.h", "view_as_real_copy_ops.h", "string_utils.h", "_native_batch_norm_legit.h", "annotate_warns.h", "DepthwiseConvKernel.h", "nonzero_static.h", "nested_to_padded_tensor_native.h", "_upsample_nearest_exact2d_cuda_dispatch.h", "ForeachUtils.h", "node_hashing.h", "vander_native.h", "rpc.h", "_pdist_backward_ops.h", "_weight_norm.h", "acos_meta.h", "MemoryFormat.h", "var_mean_compositeexplicitautograd_dispatch.h", "matrix_power_native.h", "hardsigmoid_ops.h", "copysign_meta.h", "linalg_tensorinv_native.h", "upsample_nearest3d_meta.h", "rref_interface.h", "smooth_l1_loss_ops.h", "_version.h", "diagonal.h", "replication_pad2d_backward.h", "fft_rfftn_ops.h", "poisson_cpu_dispatch.h", "special_spherical_bessel_j0_native.h", "log_normal_cuda_dispatch.h", "_cast_Long_ops.h", "inline_forked_closures.h", "special_polygamma_native.h", "fft_rfft2.h", "special_softmax_ops.h", "miopen_rnn_backward_native.h", "cudnn_convolution_transpose.h", "_thnn_fused_lstm_cell.h", "flipud_native.h", "mps_convolution_backward.h", "linalg_multi_dot_native.h", "agent_utils.h", "_embedding_bag_cpu_dispatch.h", "prod_meta.h", "align_tensors_native.h", "SmallBuffer.h", "slow_conv_transpose3d.h", "mixed_data_type.h", "mkldnn_adaptive_avg_pool2d_native.h", "sqrt_native.h", "asin_native.h", "tensor_aten_ops.h", "log_sigmoid.h", "BucketizationUtils.h", "addmv_meta.h", "_to_sparse_csc_cuda_dispatch.h", "replication_pad1d_backward_ops.h", "linalg_vector_norm.h", "_sparse_csr_sum_ops.h", "linspace_ops.h", "Utils.h", "_cufft_get_plan_cache_max_size_ops.h", "upsample_nearest3d_backward_cuda_dispatch.h", "huber_loss_backward_native.h", "avg_pool2d_backward_cuda_dispatch.h", "isclose.h", "_has_compatible_shallow_copy_type_ops.h", "ATen_fwd.h", "BinaryOps.h", "cudnn_convolution_transpose_ops.h", "fft_ifftn.h", "prod_compositeexplicitautograd_dispatch.h", "special_log_ndtr_native.h", "gru_cell_native.h", "to_dense_native.h", "special_i1e.h", "InferenceMode.h", "linalg_ldl_solve_meta.h", "_sparse_compressed_tensor_unsafe_ops.h", "torchscript_functions.h", "_upsample_bilinear2d_aa_backward_meta.h", "SymIntArrayRef.h", "_adaptive_avg_pool3d_native.h", "_scaled_dot_product_attention_math_compositeimplicitautograd_dispatch.h", "TensorIteratorInternal.h", "tril_indices_cpu_dispatch.h", "_foreach_neg.h", "TensorBody.h", "selu_ops.h", "new_zeros_ops.h", "gt.h", "_batch_norm_impl_index_backward.h", "sparse_compressed_tensor.h", "linear_ops.h", "engine.h", "complex.h", "vol2col.h", "_scaled_dot_product_efficient_attention_backward_native.h", "_is_all_true.h", "_foreach_abs_native.h", "as_strided_scatter_compositeexplicitautogradnonfunctional_dispatch.h", "linalg_solve_ex.h", "_sparse_softmax_native.h", "miopen_rnn_backward_ops.h", "nanquantile_native.h", "from_file_native.h", "special_erfc_native.h", "grid_sampler_3d_backward_ops.h", "_reshape_alias.h", "cross_entropy_loss_compositeimplicitautograd_dispatch.h", "_add_batch_dim_native.h", "reflection_pad1d_backward.h", "NumericUtils.h", "_masked_softmax.h", "copy_ops.h", "float_power.h", "arccosh.h", "_softmax_native.h", "ReduceOps.h", "min_meta.h", "eye_compositeexplicitautograd_dispatch.h", "lu_solve.h", "or_native.h", "hooks_for_testing.h", "_upsample_nearest_exact1d.h", "_sparse_softmax_backward_data.h", "MaybeOwned.h", "special_hermite_polynomial_h_native.h", "_make_dual_ops.h", "as_strided_native.h", "module.h", "Cross.h", "max_pool3d_native.h", "_unsafe_view.h", "hardshrink_meta.h", "expand_copy_native.h", "_upsample_bilinear2d_aa_cpu_dispatch.h", "transformer.h", "upsample_nearest1d_backward_meta_dispatch.h", "nan_to_num_compositeexplicitautograd_dispatch.h", "linalg_matrix_rank.h", "freeze_module.h", "col2im_native.h", "indices_copy.h", "_is_any_true_ops.h", "soft_margin_loss.h", "_foreach_log1p_ops.h", "slow_conv_dilated3d.h", "var_cpu_dispatch.h", "to_sparse_bsr_native.h", "upsample_bilinear2d_backward_cuda_dispatch.h", "sym_constrain_range_ops.h", "rnn_relu_cell_compositeimplicitautograd_dispatch.h", "squeeze_native.h", "lcm.h", "slow_conv_transpose3d_cpu_dispatch.h", "functional_bfloat16.h", "triu_native.h", "unbind_copy.h", "stl_bind.h", "_sparse_csr_prod.h", "meshgrid_ops.h", "upsample_nearest2d_backward_compositeexplicitautogradnonfunctional_dispatch.h", "fft_irfft_ops.h", "_choose_qparams_per_tensor_ops.h", "multiply_ops.h", "linalg_inv.h", "FunctionRef.h", "convolution_overrideable_native.h", "_foreach_tan.h", "minimum.h", "_conj_physical_ops.h", "conv3d_native.h", "nan_to_num_cuda_dispatch.h", "mkldnn_reorder_conv3d_weight.h", "ReduceOps.h", "mkldnn_max_pool2d_backward.h", "_foreach_norm_ops.h", "hardswish_backward_ops.h", "less_equal_native.h", "fft_hfft2_compositeimplicitautograd_dispatch.h", "_sparse_sum_ops.h", "abs_native.h", "less_equal.h", "relu_ops.h", "square_native.h", "qscheme_ops.h", "geometric_meta_dispatch.h", "upsample_nearest3d_cpu_dispatch.h", "tensor.h", "sum_cuda_dispatch.h", "special_logsumexp_ops.h", "combined_traceback.h", "python_engine.h", "enum_type.h", "crow_indices_copy_ops.h", "pthreadpool.h", "interpreter.h", "argwhere_ops.h", "_foreach_log10.h", "is_pinned_native.h", "LegacyVmapTransforms.h", "PixelShuffleKernel.h", "baddbmm_ops.h", "special_shifted_chebyshev_polynomial_v_ops.h", "clamp_native.h", "TensorAdvancedIndexing.h", "logsumexp.h", "conv_depthwise3d_compositeexplicitautograd_dispatch.h", "llvmMathExtras.h", "pixelshuffle.h", "miopen_depthwise_convolution_native.h", "detach_copy.h", "_cudnn_ctc_loss_native.h", "replication_pad1d.h", "empty_strided_ops.h", "upsample_trilinear3d_cpu_dispatch.h", "negative_native.h", "_neg_view_copy.h", "_index_put_impl_cuda_dispatch.h", "_native_multi_head_attention_ops.h", "rrelu_with_noise.h", "logical_not_native.h", "clamp_min_meta.h", "fbgemm_linear_fp16_weight_fp32_activation.h", "outer_ops.h", "_reshape_from_tensor.h", "bartlett_window.h", "_foreach_sub.h", "mm.h", "Unfold2d.h", "linalg_matmul_ops.h", "geqrf.h", "geometric_cpu_dispatch.h", "padding.h", "_values_native.h", "set_data_native.h", "native_group_norm_backward_native.h", "randint_like_native.h", "batch_norm_gather_stats_with_counts_compositeexplicitautograd_dispatch.h", "special_softmax.h", "cumprod_backward_ops.h", "log_sigmoid_forward_native.h", "fft_fftn_compositeimplicitautograd_dispatch.h", "_cufft_clear_plan_cache.h", "logsumexp_native.h", "_is_all_true_ops.h", "elu_native.h", "hoist_conv_packed_params.h", "exp_meta.h", "python_variable.h", "fbgemm_linear_fp16_weight.h", "linalg_svd_compositeimplicitautograd_dispatch.h", "parse_string_literal.h", "retain_grad_ops.h", "logaddexp2.h", "Dimname.h", "std.h", "zmath.h", "fused_moving_avg_obs_fake_quant.h", "special_chebyshev_polynomial_t.h", "DispatchKeyExtractor.h", "pooling.h", "_linalg_svd.h", "is_nonzero_ops.h", "trace.h", "size_native.h", "library.h", "_histogramdd_from_bin_tensors_ops.h", "max_pool3d_with_indices.h", "_neg_view_copy_ops.h", "linalg_norm_compositeimplicitautograd_dispatch.h", "rot90_ops.h", "resolve_neg.h", "vec256.h", "type_factory.h", "indices_copy_native.h", "is_set_to_ops.h", "_int_mm_native.h", "fft_fft_compositeimplicitautograd_dispatch.h", "_upsample_bilinear2d_aa_cuda_dispatch.h", "smooth_l1_loss_meta.h", "mkldnn_rnn_layer_ops.h", "special_expm1_native.h", "signbit.h", "_adaptive_avg_pool3d_backward.h", "bernoulli_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_coo_tensor_with_dims_and_tensors_compositeexplicitautograd_dispatch.h", "_thnn_differentiable_gru_cell_backward_ops.h", "_fill_mem_eff_dropout_mask_ops.h", "max_pool3d_with_indices_backward_native.h", "_sample_dirichlet_ops.h", "exponential_cpu_dispatch.h", "linalg_vecdot.h", "_use_cudnn_ctc_loss.h", "blackman_window_compositeexplicitautograd_dispatch.h", "miopen_batch_norm.h", "_test_autograd_multiple_dispatch_view_ops.h", "convolution_overrideable.h", "q_per_channel_scales_native.h", "ts_node.h", "_cast_Short_native.h", "SmallVector.h", "histogram.h", "select_backward.h", "vec256_qint.h", "addcdiv_native.h", "vec256_int.h", "TensorDataContainer.h", "linalg_cholesky.h", "reshape.h", "simple_graph_executor_impl.h", "replication_pad2d.h", "requires_grad_native.h", "pickler.h", "_foreach_lerp_ops.h", "ConvUtils.h", "_foreach_abs_ops.h", "_nested_view_from_buffer_copy_native.h", "_linalg_slogdet_meta.h", "_scaled_dot_product_flash_attention_cuda_dispatch.h", "special_erfcx_ops.h", "linalg_eig.h", "replication_pad3d_meta.h", "_lu_with_info_ops.h", "_lu_with_info_native.h", "to_sparse_bsr.h", "sparse_compressed_tensor_ops.h", "nll_loss2d_compositeimplicitautograd_dispatch.h", "slow_conv_dilated2d_native.h", "signal_handler.h", "to_dense_ops.h", "_convolution_native.h", "context.h", "argsort_native.h", "python_nn_functions.h", "mkldnn_max_pool2d_backward_ops.h", "adaptive_max_pool3d_backward_ops.h", "resize_meta_dispatch.h", "column_stack_native.h", "replication_pad3d_backward.h", "symbolic_shape_registry_util.h", "shape_inference.h", "_sparse_semi_structured_linear_ops.h", "_upsample_nearest_exact3d_compositeexplicitautogradnonfunctional_dispatch.h", "_pack_padded_sequence_backward_ops.h", "Event.h", "trie.h", "python_scalars.h", "SortStable.h", "max_unpool3d_native.h", "_empty_affine_quantized_compositeexplicitautograd_dispatch.h", "cosh_ops.h", "special_shifted_chebyshev_polynomial_u_ops.h", "_sparse_bsc_tensor_unsafe_ops.h", "batch_norm.h", "warnings.h", "_test_warn_in_autograd_ops.h", "MPSHooksInterface.h", "sym_numel.h", "imag.h", "is_distributed_ops.h", "_adaptive_avg_pool2d.h", "expm1.h", "_cufft_set_plan_cache_max_size_ops.h", "PyInterpreter.h", "_int_mm_ops.h", "expr.h", "source_range_serialization.h", "_fused_adamw_native.h", "matrix_exp_backward.h", "alias_ops.h", "adaptive_avg_pool3d_backward_native.h", "_standard_gamma_cuda_dispatch.h", "ormqr_native.h", "linalg_tensorsolve_native.h", "_index_put_impl.h", "upsampling.h", "CUDATest.h", "indices_native.h", "_foreach_exp.h", "PrivateUse1HooksInterface.h", "_to_sparse_csr_cuda_dispatch.h", "_scaled_dot_product_flash_attention_backward.h", "_dimV_ops.h", "median_native.h", "_fused_adamw.h", "resolver.h", "max_meta.h", "clamp_max_ops.h", "special_polygamma.h", "permute_ops.h", "_ctc_loss_backward_native.h", "_foreach_floor.h", "_flash_attention_forward_cuda_dispatch.h", "special_i0e_meta.h", "log_softmax.h", "randn_native.h", "upsample_nearest2d_compositeexplicitautogradnonfunctional_dispatch.h", "_foreach_acos_ops.h", "_thnn_fused_lstm_cell_ops.h", "HIPAllocatorMasqueradingAsCUDA.h", "log10_ops.h", "sym_numel_ops.h", "ccol_indices_ops.h", "jit_type_base.h", "remove_expands.h", "transpose_copy_ops.h", "EmptyTensor.h", "adam.h", "Activation.h", "isreal_ops.h", "lift_fresh_copy_ops.h", "_foreach_add.h", "index_copy_meta.h", "convolution_backward_overrideable.h", "_upsample_bicubic2d_aa_compositeexplicitautogradnonfunctional_dispatch.h", "IndexingUtils.h", "functional_base.h", "_sample_dirichlet_cuda_dispatch.h", "_unique_ops.h", "mkldnn_adaptive_avg_pool2d_ops.h", "dropout.h", "meshgrid_native.h", "fft_fft2_ops.h", "elu_backward_ops.h", "reshape_ops.h", "_foreach_exp_ops.h", "_foreach_acos.h", "fmin_native.h", "upsample_bilinear2d_backward_meta.h", "_sparse_bsr_tensor_unsafe_compositeimplicitautograd_dispatch.h", "module.h", "_scaled_dot_product_efficient_attention_native.h", "logaddexp2_meta.h", "_foreach_cos_ops.h", "stack_ops.h", "eval.h", "_nested_tensor_from_mask_left_aligned_native.h", "TypeInfo.h", "repeat.h", "view_as_real_copy.h", "col_indices_native.h", "lexer.h", "frexp.h", "tensor.h", "quantized_batch_norm_ops.h", "MathBitsFallback.h", "linalg_matmul.h", "_upsample_bilinear2d_aa_compositeexplicitautogradnonfunctional_dispatch.h", "max_pool2d_with_indices_meta.h", "range_native.h", "slice_backward.h", "unsafe_split_with_sizes_native.h", "_cummax_helper_ops.h", "prelu_ops.h", "linalg_vector_norm_cpu_dispatch.h", "prod_ops.h", "batch_norm_update_stats.h", "inplace_check.h", "prepack_folding.h", "clear_undefinedness.h", "DeviceGuardImplInterface.h", "embedding_backward.h", "silu_backward_ops.h", "slow_conv3d_native.h", "_scaled_dot_product_flash_attention_ops.h", "cudnn_convolution_add_relu_cuda_dispatch.h", "cumsum_native.h", "file_check.h", "batch_norm_backward_elemt_ops.h", "python_tracer.h", "logcumsumexp_native.h", "avg_pool2d_cuda_dispatch.h", "boxing.h", "prelu_native.h", "masked_select_backward_native.h", "_cudnn_ctc_loss_ops.h", "_upsample_nearest_exact2d_ops.h", "arcsinh_native.h", "_thnn_differentiable_lstm_cell_backward_ops.h", "finalize.h", "refine_names_ops.h", "jit_log.h", "_transformer_encoder_layer_fwd_cpu_dispatch.h", "_fake_quantize_learnable_per_channel_affine_backward_native.h", "_nested_tensor_softmax_with_shape_ops.h", "hamming_window_ops.h", "batchnorm.h", "XnnpackUtils.h", "special_xlog1py.h", "adaptive_max_pool3d_backward_meta.h", "tanh_native.h", "vander_compositeimplicitautograd_dispatch.h", "hardsigmoid_backward_meta.h", "special_xlog1py_native.h", "_cufft_get_plan_cache_max_size_native.h", "fmod_native.h", "_standard_gamma_grad_native.h", "mkldnn_rnn_layer_backward_cpu_dispatch.h", "unique_consecutive.h", "mish_native.h", "_foreach_log.h", "lift_native.h", "module.h", "_standard_gamma_compositeexplicitautograd_dispatch.h", "_log_softmax_meta.h", "_stack.h", "fft_fft_native.h", "diagonal_copy.h", "TensorUtils.h", "op_allowlist.h", "median.h", "zeros.h", "_flash_attention_forward.h", "_foreach_addcdiv_native.h", "FakeQuantAffine.h", "ravel_native.h", "add_if_then_else.h", "nll_loss2d_forward_cpu_dispatch.h", "_nnpack_available_native.h", "atan2_ops.h", "_convert_indices_from_coo_to_csr_native.h", "GPUTrace.h", "TensorFactories.h", "full_ops.h", "vsplit.h", "conv_serialization.h", "_foreach_log2.h", "bartlett_window_compositeexplicitautograd_dispatch.h", "thnn_conv2d_compositeimplicitautograd_dispatch.h", "FakeGuardImpl.h", "RegistrationHandleRAII.h", "igamma.h", "OperationUtils.h", "SymInt.h", "arcsin.h", "slice_scatter_compositeexplicitautogradnonfunctional_dispatch.h", "fft_ihfftn.h", "_mkldnn_reshape_native.h", "scaled_dot_product_attention.h", "contiguous_ops.h", "fake_quantize_per_tensor_affine_cachemask_backward_ops.h", "_fused_adam_compositeexplicitautograd_dispatch.h", "dense_dim_ops.h", "kaiser_window_native.h", "frac_native.h", "i0_native.h", "reflection_pad2d_backward_ops.h", "baddbmm_meta.h", "xlogy_meta.h", "max_pool2d_with_indices_backward.h", "TensorTopK.h", "_cufft_set_plan_cache_max_size.h", "floor_divide.h", "SparseCsrTensorUtils.h", "_to_sparse_csr.h", "empty_compositeexplicitautograd_dispatch.h", "randint_like_compositeexplicitautograd_dispatch.h", "divide_native.h", "_linalg_solve_ex_ops.h", "is_conj.h", "and_native.h", "is_neg_native.h", "fft_irfft_compositeimplicitautograd_dispatch.h", "allclose.h", "nll_loss_forward_compositeexplicitautogradnonfunctional_dispatch.h", "erfc_native.h", "bernoulli_meta_dispatch.h", "register_ops_utils.h", "_upsample_bicubic2d_aa_backward_cuda_dispatch.h", "rnn.h", "special_shifted_chebyshev_polynomial_t_ops.h", "special_gammainc_native.h", "import_source.h", "upsample_trilinear3d_meta.h", "ceil_meta.h", "slow_conv_dilated3d_native.h", "_index_put_impl_compositeexplicitautograd_dispatch.h", "cpython_defs.h", "_shape_as_tensor_native.h", "log_softmax_compositeexplicitautograd_dispatch.h", "arctanh.h", "normal_cpu_dispatch.h", "movedim.h", "cpp_prefix.h", "peephole_dict_idioms.h", "tensorpipe_agent.h", "batch_norm_elemt_cuda_dispatch.h", "_efficientzerotensor.h", "vec256_float_vsx.h", "resolve_conj_native.h", "repeat_native.h", "conv2d_native.h", "_embedding_bag_dense_backward_ops.h", "lu_unpack.h", "python_symnode.h", "Sorting.h", "tensor.h", "_foreach_tanh_ops.h", "lt_native.h", "convolution_backward_overrideable_ops.h", "group_norm.h", "Variadic.h", "fft_fft_ops.h", "MTIAHooksInterface.h", "is_neg.h", "bucketize_ops.h", "frac.h", "backend_debug_handler.h", "empty_quantized_ops.h", "sort.h", "_prelu_kernel_backward_native.h", "fill_diagonal_native.h", "multilabel_margin_loss_forward.h", "linear.h", "linalg_lu_factor.h", "_sparse_log_softmax_backward_data.h", "hinge_embedding_loss_ops.h", "_sparse_csr_sum.h", "nll_loss2d_forward_cuda_dispatch.h", "multiply_native.h", "batch_norm_gather_stats_ops.h", "error_report.h", "mkldnn_adaptive_avg_pool2d_backward.h", "_sparse_log_softmax_backward_data_native.h", "nll_loss_backward_cpu_dispatch.h", "SavedTensorHooks.h", "upsample_nearest3d_meta_dispatch.h", "special_hermite_polynomial_h.h", "fake_quantize_per_tensor_affine_cachemask_backward.h", "stride_native.h", "broadcast_tensors.h", "TypeTraits.h", "scalar_tensor_ops.h", "sparse_mask_ops.h", "hsplit_native.h", "glu_jvp.h", "_cummin_helper_ops.h", "SoftmaxKernel.h", "sparse.h", "sparse_dim_native.h", "_cudnn_rnn_compositeexplicitautograd_dispatch.h", "linalg_qr_native.h", "upsample_bicubic2d_backward_meta_dispatch.h", "adaptive_max_pool3d_native.h", "special_scaled_modified_bessel_k1_native.h", "_sparse_mm.h", "base.h", "sym_storage_offset_native.h", "_conv_depthwise2d_cuda_dispatch.h", "ivalue.h", "_nnpack_spatial_convolution.h", "all_meta.h", "movedim_ops.h", "_aminmax_native.h", "triplet_margin_loss_ops.h", "fractional_max_pool2d_backward.h", "miopen_rnn_ops.h", "python_dispatch.h", "cholesky_native.h", "upsample_trilinear3d_backward_cpu_dispatch.h", "squeeze_ops.h", "split_native.h", "renorm_ops.h", "sym_constrain_range_for_size_compositeexplicitautograd_dispatch.h", "can_cast_ops.h", "sparse_csc_tensor.h", "less_equal_ops.h", "segment_reduce_native.h", "_sparse_broadcast_to_copy_ops.h", "special_log_ndtr_meta.h", "lower_tuples.h", "choose_qparams_optimized_ops.h", "sinh_ops.h", "exp_ops.h", "miopen_convolution_native.h", "cumprod_cuda_dispatch.h", "gil.h", "_assert_async.h", "_cholesky_solve_helper_ops.h", "_nested_tensor_size_native.h", "pinverse_native.h", "SerialStackImpl.h", "all_native.h", "fft_ifftshift.h", "profiler_kineto.h", "insert_quant_dequant.h", "fill_diagonal_ops.h", "upsample_nearest3d.h", "sort_cuda_dispatch.h", "CUDAGraph.h", "normal_native.h", "triu_ops.h", "binary_cross_entropy_with_logits_compositeexplicitautograd_dispatch.h", "_unsafe_index_native.h", "slow_conv_dilated3d_compositeexplicitautograd_dispatch.h", "alias_copy.h", "_thnn_fused_lstm_cell_backward_native.h", "_scaled_dot_product_flash_attention_backward_cuda_dispatch.h", "special_gammainc.h", "rand_compositeexplicitautograd_dispatch.h", "sleef.h", "sym_constrain_range_native.h", "qr.h", "values_copy_native.h", "slice_copy_compositeexplicitautograd_dispatch.h", "_fake_quantize_learnable_per_channel_affine_native.h", "_native_multi_head_attention_compositeexplicitautograd_dispatch.h", "_test_optional_floatlist_cpu_dispatch.h", "special_bessel_j0_ops.h", "_sparse_coo_tensor_unsafe_native.h", "is_leaf_ops.h", "_native_batch_norm_legit_no_training.h", "dequantize_native.h", "row_stack.h", "_sparse_coo_tensor_with_dims_ops.h", "unfold_copy_ops.h", "_upsample_bicubic2d_aa_meta.h", "clamp_min.h", "conv_tbc_ops.h", "backend_detail.h", "function_schema.h", "std_compositeimplicitautograd_dispatch.h", "nll_loss_nd.h", "ceil_div.h", "nonzero_static_ops.h", "div_cuda_dispatch.h", "sigmoid_native.h", "_adaptive_avg_pool2d_backward_ops.h", "_foreach_lgamma.h", "erfinv_native.h", "slow_conv3d_compositeimplicitautograd_dispatch.h", "miopen_depthwise_convolution_cuda_dispatch.h", "smooth_l1_loss_backward_native.h", "replication_pad2d_backward_native.h", "glu_jvp_native.h", "wrap_outputs.h", "threshold_backward_meta.h", "add_ops.h", "PlumbingHelper.h", "adaptive_max_pool2d_backward.h", "fake_quantize_per_channel_affine_cachemask_native.h", "lcm_meta.h", "nonzero_numpy_ops.h", "dstack.h", "static.h", "tril_indices_native.h", "repeat_interleave_cpu_dispatch.h", "scaled_dot_product_attention_ops.h", "variable_factories.h", "silu_meta.h", "hash.h", "unsqueeze.h", "_sparse_mm_reduce_impl_backward.h", "native_dropout_cuda_dispatch.h", "unsafe_chunk.h", "special_legendre_polynomial_p.h", "_pad_enum_native.h", "symbolic_shape_runtime_fusion.h", "_validate_sparse_csr_tensor_args_ops.h", "CompositeExplicitAutogradFunctions_inl.h", "layer_norm_compositeimplicitautograd_dispatch.h", "diff_native.h", "_upsample_bicubic2d_aa_backward_meta_dispatch.h", "Copy.h", "Device.h", "upsample_bicubic2d_backward_cpu_dispatch.h", "bitwise_and_native.h", "init.h", "slow_conv_dilated3d_cuda_dispatch.h", "exp.h", "logaddexp2_native.h", "unpickled_python_call.h", "sort_cpu_dispatch.h", "dot_ops.h", "divide.h", "_is_zerotensor.h", "histogramdd_native.h", "special_modified_bessel_i1_ops.h", "upsample_linear1d_ops.h", "_grid_sampler_2d_cpu_fallback_backward.h", "c10d.h", "sparse_resize.h", "miopen_rnn_native.h", "_foreach_trunc_ops.h", "special_chebyshev_polynomial_u_ops.h", "cosh.h", "take_along_dim_ops.h", "insert_guards.h", "ne.h", "is_signed_ops.h", "parse_operators.h", "_foreach_sigmoid.h", "view_as_native.h", "_foreach_log2_native.h", "_int_mm.h", "_debug_has_internal_overlap.h", "tensor_types.h", "constants.h", "fft_hfft.h", "mH.h", "remove_dropout.h", "cpp_codegen.h", "randn_compositeexplicitautograd_dispatch.h", "_to_copy.h", "elu_backward_native.h", "indices.h", "special_round_native.h", "_test_autograd_multiple_dispatch_view_copy_ops.h", "batch_norm_gather_stats_cuda_dispatch.h", "_upsample_bicubic2d_aa_native.h", "_sparse_coo_tensor_unsafe.h", "cauchy_cpu_dispatch.h", "log_sigmoid_forward.h", "linalg_norm_native.h", "custom_class_detail.h", "Fill.h", "PythonTorchFunctionTLS.h", "bmm_ops.h", "ceil_native.h", "special_erfc.h", "crow_indices_copy.h", "argmin_compositeexplicitautogradnonfunctional_dispatch.h", "silu_backward_meta.h", "lstm.h", "pdist_ops.h", "_upsample_bilinear2d_aa_backward_cuda_dispatch.h", "geometric_compositeexplicitautograd_dispatch.h", "result_type_ops.h", "threshold.h", "max_pool1d_with_indices_native.h", "_spdiags_cpu_dispatch.h", "reshape_as.h", "flatbuffer_serializer_jit.h", "linalg_lu_ops.h", "SampledAddmmKernel.h", "bitwise_right_shift_meta.h", "batch_norm_backward_elemt_cuda_dispatch.h", "kron.h", "column_stack_ops.h", "Functions.h", "conv.h", "inline_autodiff_subgraphs.h", "conv2d.h", "_make_per_tensor_quantized_tensor_ops.h", "linalg_lstsq_native.h", "nll_loss2d_forward_ops.h", "resize_compositeexplicitautograd_dispatch.h", "mean_ops.h", "_sparse_coo_tensor_with_dims_and_tensors_native.h", "log_sigmoid_backward_native.h", "lower_grad_of.h", "exponential_compositeexplicitautograd_dispatch.h", "is_complex_ops.h", "zeros_ops.h", "frozen_ops_to_mkldnn.h", "max_pool2d.h", "_foreach_tan_ops.h", "permute_native.h", "_foreach_mul_native.h", "greater_equal_ops.h", "device_type_analysis.h", "linalg_tensorsolve_ops.h", "linalg_cholesky_ex_native.h", "upsample_nearest2d_backward_meta_dispatch.h", "_foreach_floor_ops.h", "logging.h", "avg_pool3d_backward_native.h", "_convolution_ops.h", "_test_serialization_subcmul.h", "backend_init.h", "_foreach_lgamma_native.h", "ATen_pch.h", "_fused_dropout_cuda_dispatch.h", "expanding_array.h", "gelu_backward_meta.h", "split_copy.h", "native_group_norm_backward_cpu_dispatch.h", "lerp_meta.h", "_sobol_engine_initialize_state.h", "normal.h", "logit_backward_meta_dispatch.h", "sparse_bsc_tensor.h", "msort_native.h", "to_mkldnn.h", "FunctionalizeInterpreter.h", "kron_native.h", "edit_distance.h", "conv_depthwise3d_cuda_dispatch.h", "adaptive_max_pool1d.h", "_nested_tensor_from_mask.h", "nll_loss2d_backward_cpu_dispatch.h", "cudnn_batch_norm_backward_cuda_dispatch.h", "PackedParams.h", "layer_norm.h", "tril_indices.h", "_nnz_ops.h", "special_log1p_ops.h", "block_diag_ops.h", "pad_ops.h", "data.h", "ArrayRef.h", "_ctc_loss_backward.h", "remainder_meta.h", "conj_ops.h", "quantized_batch_norm.h", "import.h", "avg_pool2d_backward_cpu_dispatch.h", "input-archive.h", "resize_as_sparse_native.h", "select_scatter_native.h", "memory_snapshot.h", "sigmoid.h", "sspaddmm_native.h", "full_like.h", "maximum_native.h", "python_sparse_functions.h", "tensor.h", "subtract_ops.h", "reflection_pad2d_native.h", "combinations.h", "arccosh_native.h", "Generator.h", "cos_meta.h", "log_normal_cpu_dispatch.h", "scatter_reduce.h", "div_ops.h", "arcsinh_ops.h", "cov_compositeimplicitautograd_dispatch.h", "sign_meta.h", "_foreach_erf.h", "special_bessel_j1.h", "_upsample_bilinear2d_aa_native.h", "maximum.h", "_cudnn_rnn_flatten_weight.h", "fmod_ops.h", "vec128_float_neon.h"]}, "less": ["aot_inductor_interface.h", "_foreach_sinh_cpu_dispatch.h", "_foreach_sqrt_cpu_dispatch.h", "_foreach_add_cpu_dispatch.h", "python_return_types.h", "_foreach_reciprocal_cpu_dispatch.h", "_foreach_clamp_max_cpu_dispatch.h", "_foreach_neg_cpu_dispatch.h", "_foreach_log10_cpu_dispatch.h", "_foreach_asin_cpu_dispatch.h", "is_pinned_cuda_dispatch.h", "floor_divide_compositeimplicitautograd_dispatch.h", "_embedding_bag_backward_compositeimplicitautograd_dispatch.h", "_foreach_log2_cpu_dispatch.h", "_foreach_tanh_cpu_dispatch.h", "context.h", "_foreach_norm_cpu_dispatch.h", "argsort_cuda_dispatch.h", "qnnpack.h", "bitwise_or_compositeimplicitautograd_dispatch.h", "ORTHooksInterface.h", "_foreach_maximum_cpu_dispatch.h", "_foreach_sin_cpu_dispatch.h", "aot_inductor_model_container.h", "special_hermite_polynomial_h_compositeimplicitautograd_dispatch.h", "special_chebyshev_polynomial_u_compositeimplicitautograd_dispatch.h", "_unsafe_index_cuda_dispatch.h", "_foreach_atan_cpu_dispatch.h", "dense_dim_cuda_dispatch.h", "sparse_dim_cpu_dispatch.h", "deleter.h", "_foreach_sign_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_v_compositeimplicitautograd_dispatch.h", "_foreach_cos_cpu_dispatch.h", "reverse_iterator.h", "_pin_memory_cuda_dispatch.h", "_foreach_sigmoid_cpu_dispatch.h", "cudnn_convolution_compositeexplicitautograd_dispatch.h", "_foreach_acos_cpu_dispatch.h", "_foreach_ceil_cpu_dispatch.h", "math_compat.h", "aot_inductor_model.h", "either.h", "special_chebyshev_polynomial_w_compositeimplicitautograd_dispatch.h", "_foreach_frac_cpu_dispatch.h", "_foreach_erfc_cpu_dispatch.h", "argsort_compositeexplicitautograd_dispatch.h", "_foreach_clamp_min_cpu_dispatch.h", "unbind_compositeimplicitautogradnestedtensor_dispatch.h", "bitwise_and_compositeimplicitautograd_dispatch.h", "_foreach_tan_cpu_dispatch.h", "_foreach_copy_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_u_compositeimplicitautograd_dispatch.h", "_foreach_sub_cpu_dispatch.h", "_foreach_cosh_cpu_dispatch.h", "_foreach_minimum_cpu_dispatch.h", "_foreach_abs_cpu_dispatch.h", "argsort_cpu_dispatch.h", "_foreach_log_cpu_dispatch.h", "cuda_graph_fuser.h", "_foreach_erf_cpu_dispatch.h", "_foreach_lgamma_cpu_dispatch.h", "_foreach_expm1_cpu_dispatch.h", "_foreach_lerp_cpu_dispatch.h", "_foreach_floor_cpu_dispatch.h", "variant.h", "_foreach_log1p_cpu_dispatch.h", "_scaled_dot_product_flash_attention_backward_cpu_dispatch.h", "_foreach_mul_cpu_dispatch.h", "_unsafe_index_cpu_dispatch.h", "auto_gil.h", "sparse_dim_cuda_dispatch.h", "_foreach_pow_cpu_dispatch.h", "memory.h", "special_legendre_polynomial_p_compositeimplicitautograd_dispatch.h", "_foreach_div_cpu_dispatch.h", "_assert_tensor_metadata_compositeimplicitautograd_dispatch.h", "special_laguerre_polynomial_l_compositeimplicitautograd_dispatch.h", "_foreach_round_cpu_dispatch.h", "special_shifted_chebyshev_polynomial_t_compositeimplicitautograd_dispatch.h", "_foreach_zero_cpu_dispatch.h", "_foreach_exp_cpu_dispatch.h", "_scaled_dot_product_flash_attention_cpu_dispatch.h", "UnaryConstants.h", "FlushDenormal.h", "special_shifted_chebyshev_polynomial_w_compositeimplicitautograd_dispatch.h", "import_legacy.h", "special_chebyshev_polynomial_t_compositeimplicitautograd_dispatch.h", "linalg.h", "in_place.h", "_foreach_addcdiv_cpu_dispatch.h", "SingletonSymNodeImpl.h", "_foreach_trunc_cpu_dispatch.h", "cuda_lazy_init.h", "_foreach_addcmul_cpu_dispatch.h", "special_chebyshev_polynomial_v_compositeimplicitautograd_dispatch.h", "special_hermite_polynomial_he_compositeimplicitautograd_dispatch.h", "bitwise_xor_compositeimplicitautograd_dispatch.h", "ParallelNativeTBB.h", "dense_dim_cpu_dispatch.h"], "more": ["ReducedPrecisionFloatGemvFastPathKernel.h", "_weight_int4pack_mm_for_cpu_ops.h", "c_shim_cuda.h", "_fused_adam_cpu_dispatch.h", "unwind.h", "_scaled_dot_product_cudnn_attention_backward_cuda_dispatch.h", "debug_macros.h", "vec128_convert.h", "rms_norm_compositeimplicitautograd_dispatch.h", "_foreach_max_native.h", "_functional_assert_scalar_ops.h", "XPUStream.h", "sycl_runtime_wrappers.h", "fde.h", "_assert_scalar_compositeexplicitautograd_dispatch.h", "tensor_converter.h", "_nested_view_from_jagged_copy_compositeexplicitautograd_dispatch.h", "_lazy_clone_ops.h", "indexing.h", "libkineto.h", "Lazy.h", "floor_divide_compositeexplicitautograd_dispatch.h", "_weight_int8pack_mm.h", "pybind.h", "ActivityType.h", "CachingDeviceAllocator.h", "adaptive_avg_pool1d_compositeexplicitautograd_dispatch.h", "_fused_adagrad_native.h", "oneDNN.h", "_functional_assert_scalar_native.h", "_scaled_grouped_mm_cuda_dispatch.h", "dwarf_enums.h", "ck_gemm.h", "_convert_weight_to_int4pack_for_cpu_native.h", "vec128_bfloat16_neon.h", "_wrapped_linear_prepack_compositeimplicitautograd_dispatch.h", "Gelu.h", "XPUMacros.h", "_nested_get_ragged_idx_native.h", "_nested_view_from_jagged_ops.h", "vec256_convert.h", "_linalg_eigvals_ops.h", "_scaled_dot_product_cudnn_attention_native.h", "_cslt_sparse_mm_search_cuda_dispatch.h", "_scaled_grouped_mm_ops.h", "CachingHostAllocator.h", "AbortHandler.h", "_sparse_semi_structured_apply_cuda_dispatch.h", "ck_gemm_template.h", "rms_norm_ops.h", "_batch_norm_no_update_ops.h", "any_compositeexplicitautograd_dispatch.h", "_unsafe_masked_index.h", "DeviceAccelerator.h", "masked_scatter_backward_compositeexplicitautograd_dispatch.h", "library.h", "debug_info.h", "xpu.h", "ACLUtils.h", "vec128_half_neon.h", "XPUContext.h", "ActivityProfilerInterface.h", "vec_float.h", "CUDAAllocatorConfig.h", "PhiloxCudaState.h", "_sparse_semi_structured_addmm_ops.h", "Stream.h", "_jagged_to_padded_dense_forward_native.h", "model_container.h", "_sparse_semi_structured_apply.h", "Float8_e5m2fnuz.h", "kai_pack.h", "_assert_tensor_metadata_meta_dispatch.h", "_dyn_quant_pack_4bit_weight.h", "_print_native.h", "oneDNNContext.h", "_batch_norm_no_update_compositeexplicitautograd_dispatch.h", "Utils.h", "utils_cuda.h", "_scaled_dot_product_flash_attention_for_cpu_cpu_dispatch.h", "scalar_to_tensor.h", "_lazy_clone_native.h", "attention.h", "split_with_sizes_copy_cuda_dispatch.h", "linalg_eigvals_cpu_dispatch.h", "_chunk_cat_native.h", "_cudnn_attention_forward.h", "_convert_weight_to_int4pack_cuda_dispatch.h", "model.h", "shim.h", "dense_dim_compositeexplicitautograd_dispatch.h", "line_number_program.h", "_chunk_cat_compositeexplicitautograd_dispatch.h", "kai_kernels.h", "_nested_view_from_jagged_copy_native.h", "rms_norm_native.h", "utils.h", "_scaled_dot_product_cudnn_attention_ops.h", "_nested_compute_contiguous_strides_offsets_cpu_dispatch.h", "vec256_mask.h", "NestedTensorMath.h", "_safe_softmax.h", "_nested_view_from_jagged.h", "_nested_get_ragged_idx.h", "sparse_dim_compositeexplicitautograd_dispatch.h", "Gelu.h", "_weight_int4pack_mm_native.h", "_spsolve.h", "rms_norm.h", "_nested_from_padded_tensor.h", "avg_pool1d_compositeexplicitautograd_dispatch.h", "fast_symbolizer.h", "_wrapped_quantized_linear_prepacked_ops.h", "ViewFuncs.h", "_nested_compute_contiguous_strides_offsets.h", "upsample_bilinear2d_compositeexplicitautograd_dispatch.h", "_fused_sgd_compositeexplicitautograd_dispatch.h", "_convert_weight_to_int4pack.h", "Float8_e4m3fnuz-inl.h", "GdsFile.h", "_ctc_loss_meta_dispatch.h", "_padded_dense_to_jagged_forward_ops.h", "_sparse_semi_structured_mm_native.h", "_scaled_dot_product_flash_attention_for_cpu_ops.h", "xpu.h", "ViewFuncs.h", "_foreach_rsqrt_compositeexplicitautograd_dispatch.h", "interface.h", "_dyn_quant_pack_4bit_weight_native.h", "_batch_norm_no_update_native.h", "time_since_epoch.h", "_scaled_dot_product_attention_math_for_mps_native.h", "_print.h", "_int_mm_cpu_dispatch.h", "_unsafe_masked_index_put_accumulate_native.h", "_foreach_max_compositeexplicitautograd_dispatch.h", "_fused_sgd_ops.h", "_nested_get_values_copy_ops.h", "_nested_get_jagged_dummy.h", "LoggingAPI.h", "_nested_get_values_copy.h", "vec_convert.h", "COWDeleter.h", "shim_mkldnn.h", "cpu.h", "_scaled_dot_product_flash_attention_for_cpu_native.h", "ParallelGuard.h", "socket_fmt.h", "_nested_get_max_seqlen_native.h", "_mixed_dtypes_linear_ops.h", "_scaled_dot_product_flash_attention_for_cpu_backward.h", "_test_parallel_materialize_native.h", "linalg_eigvals_cuda_dispatch.h", "_nested_get_lengths_native.h", "BlasBackend.h", "generated_serialization_types.h", "HPUHooksInterface.h", "_wrapped_quantized_linear_prepacked_native.h", "_amp_update_scale_cpu_dispatch.h", "vec_double.h", "generic_math.h", "_chunk_cat_cuda_dispatch.h", "utils.h", "_mixed_dtypes_linear_cuda_dispatch.h", "_scaled_dot_product_fused_attention_overrideable_backward.h", "gil_safe_call_once.h", "qlinear.h", "_test_parallel_materialize_compositeexplicitautograd_dispatch.h", "_scaled_dot_product_cudnn_attention_cuda_dispatch.h", "_assert_scalar_ops.h", "_scaled_dot_product_attention_math_for_mps.h", "_batch_norm_with_update_cpu_dispatch.h", "experiments-config.h", "_sparse_semi_structured_apply_ops.h", "_foreach_rsqrt_cuda_dispatch.h", "batch_norm_backward_cuda_dispatch.h", "_scaled_dot_product_fused_attention_overrideable_backward_ops.h", "_jagged_to_padded_dense_forward_ops.h", "_wrapped_linear_prepack_native.h", "utils.h", "_convert_weight_to_int4pack_for_cpu_cpu_dispatch.h", "thread_local.h", "ROCmFABackend.h", "_safe_softmax_native.h", "AmpKernels.h", "_cudnn_attention_forward_ops.h", "IPUHooksInterface.h", "_nested_view_from_jagged_native.h", "ILoggerObserver.h", "_unsafe_masked_index_put_accumulate_compositeexplicitautograd_dispatch.h", "Config.h", "NestedTensorTransformerFunctions.h", "action.h", "_nested_get_values_ops.h", "Dispatch_v2.h", "ck_bgemm.h", "_sparse_semi_structured_tile_ops.h", "_functional_assert_scalar.h", "XPUException.h", "batch_norm_backward_cpu_dispatch.h", "_nested_get_values.h", "cache_entry.h", "array_ref.h", "_scaled_dot_product_flash_attention_for_cpu_backward_cpu_dispatch.h", "upsample_nearest2d_compositeexplicitautograd_dispatch.h", "TunableGemm.h", "init.h", "_nested_compute_contiguous_strides_offsets_ops.h", "Event.h", "Float8_e8m0fnu.h", "_nested_get_lengths_ops.h", "vec256_16bit_float.h", "_foreach_max.h", "kai_ukernel_interface.h", "_scaled_dot_product_fused_attention_overrideable_ops.h", "ck_types.h", "pyobject_preservation.h", "_sparse_semi_structured_tile.h", "model_container_runner_cuda.h", "_safe_softmax_ops.h", "_nested_get_values_copy_compositeexplicitautograd_dispatch.h", "vec512_mask.h", "_weight_int4pack_mm_cuda_dispatch.h", "_nested_get_max_seqlen.h", "NetworkFlow.h", "WaitCounter.h", "model_container_runner.h", "int_mm_kernel.h", "_nested_view_from_jagged_copy_ops.h", "FusedSGD.h", "_weight_int8pack_mm_ops.h", "AbstractConfig.h", "_sparse_semi_structured_tile_native.h", "_dyn_quant_matmul_4bit_cpu_dispatch.h", "eval_frame_cpp.h", "_nested_get_jagged_dummy_ops.h", "DynamicCounter.h", "unwind_error.h", "unwinder.h", "XPUFunctions.h", "vec_qint.h", "_nested_from_padded_tensor_native.h", "_nested_get_min_seqlen_ops.h", "library.h", "_embedding_bag_backward_cuda_dispatch.h", "_nested_get_min_seqlen_native.h", "_padded_dense_to_jagged_forward.h", "common.h", "ApproximateClock.h", "FusedAdam.h", "_unsafe_masked_index_put_accumulate_ops.h", "_convert_weight_to_int4pack_for_cpu.h", "vec512_convert.h", "masked_scatter_backward.h", "_scaled_dot_product_fused_attention_overrideable_native.h", "StreamTimer.h", "slice_inverse_compositeexplicitautograd_dispatch.h", "_jagged_to_padded_dense_forward_cuda_dispatch.h", "vec_half.h", "_sparse_semi_structured_mm_cuda_dispatch.h", "_convert_weight_to_int4pack_native.h", "extra_state.h", "GenericTraceActivity.h", "reduction_utils.h", "_scaled_dot_product_cudnn_attention_backward_ops.h", "_safe_softmax_compositeexplicitautograd_dispatch.h", "CUDASymmetricMemory-inl.h", "Contiguity.h", "_scaled_dot_product_fused_attention_overrideable_backward_native.h", "_linalg_eigvals_cpu_dispatch.h", "_scaled_dot_product_flash_attention_for_cpu_backward_native.h", "DeviceAccelerator.h", "exception_translation.h", "vec_n.h", "_test_parallel_materialize.h", "NestedTensorBinaryOps.h", "_dyn_quant_pack_4bit_weight_ops.h", "nvtx_observer.h", "_batch_norm_no_update.h", "c_shim_xpu.h", "cpp_conduit.h", "XPUGeneratorImpl.h", "_sparse_semi_structured_apply_dense_ops.h", "_dyn_quant_matmul_4bit_ops.h", "_nested_get_values_copy_native.h", "_weight_int8pack_mm_native.h", "common.h", "CUDAContextLight.h", "_nested_get_min_seqlen.h", "_chunk_cat_ops.h", "Module.h", "_linalg_eigvals_native.h", "_nested_get_offsets_native.h", "oss_proxy_executor.h", "masked_scatter_backward_ops.h", "vec128_reduced_precision_common_neon.h", "_amp_foreach_non_finite_check_and_unscale_cpu_dispatch.h", "_padded_dense_to_jagged_forward_cpu_dispatch.h", "cuda.h", "_sparse_semi_structured_apply_dense_native.h", "CachingHostAllocator.h", "_weight_int4pack_mm_ops.h", "arrayref_tensor.h", "_sparse_semi_structured_apply_dense_cuda_dispatch.h", "_convert_weight_to_int4pack_ops.h", "sections.h", "_weight_int4pack_mm_for_cpu_native.h", "_sparse_compressed_tensor_with_dims_ops.h", "copy_meta_dispatch.h", "utils.h", "TraceSpan.h", "Attr.h", "_unsafe_masked_index_compositeexplicitautograd_dispatch.h", "privateuse1_observer.h", "framelocals_mapping.h", "_nested_compute_contiguous_strides_offsets_cuda_dispatch.h", "slice_inverse_native.h", "_nested_get_ragged_idx_ops.h", "vec_int.h", "_padded_dense_to_jagged_forward_cuda_dispatch.h", "cpu.h", "Float8_e4m3fnuz.h", "IActivityProfiler.h", "batch_norm_backward_native.h", "_nested_get_max_seqlen_ops.h", "PixelShuffle.h", "_cudnn_attention_forward_native.h", "_batch_norm_with_update_compositeexplicitautograd_dispatch.h", "xpu.h", "mem_file.h", "nonzero_static_cuda_dispatch.h", "execution_trace_observer.h", "_nested_get_jagged_dummy_native.h", "_print_ops.h", "range_table.h", "_linalg_eigvals.h", "_unsafe_index_compositeexplicitautograd_dispatch.h", "model_container_runner_xpu.h", "_assert_scalar.h", "NestedIntSymNodeImpl.h", "TunableOp.h", "RangeUtils.h", "_wrapped_quantized_linear_prepacked_compositeimplicitautograd_dispatch.h", "_sparse_semi_structured_apply_native.h", "GemmRocblas.h", "_assert_scalar_native.h", "batch_norm_backward.h", "vec256_zarch.h", "_padded_dense_to_jagged_forward_native.h", "_sparse_semi_structured_addmm.h", "_lazy_clone.h", "_foreach_max_ops.h", "array_ref.h", "special_math.h", "Float8_e8m0fnu-inl.h", "_scaled_dot_product_cudnn_attention_backward.h", "cuda.h", "_foreach_max_cuda_dispatch.h", "_functional_assert_scalar_compositeexplicitautograd_dispatch.h", "GemmCommon.h", "SDPBackend.h", "_jagged_to_padded_dense_forward.h", "XPUDevice.h", "_unsafe_masked_index_put_accumulate.h", "variable_info.h", "_nested_from_padded_tensor_ops.h", "GemmHipblaslt.h", "output_base.h", "_foreach_rsqrt_native.h", "_scaled_dot_product_cudnn_attention_backward_native.h", "_scaled_dot_product_cudnn_attention.h", "slice_inverse.h", "_foreach_rsqrt.h", "MPSGraphSequoiaOps.h", "slice_inverse_ops.h", "_scaled_grouped_mm_native.h", "_dyn_quant_matmul_4bit_native.h", "_spsolve_ops.h", "XPUGuardImpl.h", "qconv.h", "Float8_fnuz_cvt.h", "error.h", "lexer.h", "masked_scatter_backward_native.h", "pybind.h", "_fused_sgd.h", "cpu.h", "_cslt_sparse_mm_search.h", "_fused_sgd_cuda_dispatch.h", "dwarf_symbolize_enums.h", "shim_xpu.h", "_convert_weight_to_int4pack_for_cpu_ops.h", "_sparse_compressed_tensor_with_dims.h", "_dyn_quant_matmul_4bit.h", "batch_norm_backward_ops.h", "FusedAdagrad.h", "value_and_holder.h", "_fused_adagrad_ops.h", "_fused_sgd_native.h", "_cudnn_attention_forward_cuda_dispatch.h", "_weight_int4pack_mm_for_cpu_cpu_dispatch.h", "c_shim_cpu.h", "_nested_view_from_jagged_copy.h", "overflows.h", "_embedding_bag_backward_cpu_dispatch.h", "_cslt_sparse_mm_search_native.h", "NestedTensorUtils.h", "_nested_get_offsets.h", "device_lazy_init.h", "SymbolicShapeMeta.h", "_print_compositeexplicitautograd_dispatch.h", "MAIAHooksInterface.h", "_sparse_semi_structured_mm_ops.h", "vec128.h", "PinnedMemoryAllocator.h", "_nested_get_values_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_sparse_semi_structured_mm.h", "_sparse_compressed_tensor_with_dims_compositeexplicitautograd_dispatch.h", "_linalg_eigvals_cuda_dispatch.h", "model_container_runner_cpu.h", "sve_helper.h", "XPUHooks.h", "_nested_view_from_jagged_copy_compositeexplicitautogradnonfunctional_dispatch.h", "_weight_int4pack_mm_for_cpu.h", "_batch_norm_with_update_ops.h", "_test_parallel_materialize_ops.h", "python_return_types.h", "WaitCounterDynamicBackend.h", "XPUEvent.h", "combined_traceback.h", "_wrapped_linear_prepack.h", "_jagged_to_padded_dense_forward_cpu_dispatch.h", "proxy_executor.h", "_cslt_sparse_mm_search_ops.h", "pybind.h", "_nested_get_lengths.h", "AcceleratorHooksInterface.h", "_scaled_dot_product_attention_math_for_mps_ops.h", "_fused_adagrad_cpu_dispatch.h", "_wrapped_linear_prepack_ops.h", "MetalShaderLibrary.h", "NestedTensorTransformerUtils.h", "xpu.h", "_fused_adamw_cpu_dispatch.h", "XPUDeviceProp.h", "_sparse_semi_structured_addmm_native.h", "_batch_norm_with_update_native.h", "_weight_int8pack_mm_cpu_dispatch.h", "_sparse_compressed_tensor_with_dims_native.h", "_weight_int4pack_mm.h", "_nested_get_offsets_ops.h", "ScaledGroupMM.h", "_batch_norm_with_update_cuda_dispatch.h", "_unsafe_masked_index_ops.h", "_fused_sgd_cpu_dispatch.h", "_scaled_dot_product_flash_attention_for_cpu_backward_ops.h", "_mixed_dtypes_linear_native.h", "_wrapped_quantized_linear_prepacked.h", "COW.h", "_lazy_clone_compositeexplicitautograd_dispatch.h", "rrelu_with_noise_compositeexplicitautograd_dispatch.h", "vec256_half.h", "Float8_e5m2fnuz-inl.h", "cpython_includes.h", "_foreach_rsqrt_ops.h", "_sparse_semi_structured_addmm_cuda_dispatch.h", "_unsafe_masked_index_native.h", "_sparse_semi_structured_tile_cuda_dispatch.h", "model_package_loader.h", "ActivityTraceInterface.h", "typing.h", "_batch_norm_with_update.h", "vec_common_sve.h", "_scaled_dot_product_fused_attention_overrideable_compositeexplicitautograd_dispatch.h", "communicate.h", "XPUCachingAllocator.h", "array_ref_impl.h", "vec_mask.h", "_sparse_semi_structured_apply_dense.h", "Gauge.h", "utils_xpu.h", "_chunk_cat.h", "_fused_adagrad.h", "kineto_client_interface.h", "_spsolve_native.h", "all_compositeexplicitautograd_dispatch.h", "random.h", "_scaled_grouped_mm.h", "cuda.h", "Tunable.h", "_dyn_quant_pack_4bit_weight_cpu_dispatch.h", "_scaled_dot_product_flash_attention_for_cpu.h", "cpp_shim.h", "_nested_get_values_native.h", "_scaled_dot_product_fused_attention_overrideable_backward_compositeexplicitautograd_dispatch.h", "_nested_compute_contiguous_strides_offsets_native.h", "ThreadUtil.h", "RefcountedDeleter.h", "eh_frame_hdr.h", "itt_observer.h", "_scaled_dot_product_fused_attention_overrideable.h", "_fused_adagrad_compositeexplicitautograd_dispatch.h", "_mixed_dtypes_linear.h", "sdp_utils_cpp.h", "ClientInterface.h", "Event.h", "RowwiseScaledMM.h", "python_return_types.h", "device_utils.h", "MPSGraphSonomaOps.h", "ITraceActivity.h", "_assert_tensor_metadata_compositeexplicitautograd_dispatch.h", "mkldnn_tensor.h"]}, "rpm cmd": {"less": ["/usr/bin/convert-onnx-to-caffe2", "/usr/bin/convert-caffe2-to-onnx"], "more": ["/usr/bin/torchfrtrace"]}, "rpm lib": {"more": ["/usr/lib64/python3.11/site-packages/torch/lib/libaoti_custom_ops.so"]}, "rpm symbol": {"diff": [{"old": "/usr/lib64/python3.11/site-packages/torch/test/cpu_rng_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/cpu_rng_test", "details": {"count_result": {"Removed functions": 26, "Removed variables": 87}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/native_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/native_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_Half_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_Half_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/IListRef_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/IListRef_test", "details": {"count_result": {"Removed functions": 16, "Removed variables": 10}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/tutorial_tensorexpr", "new": "/usr/lib64/python3.11/site-packages/torch/bin/tutorial_tensorexpr", "details": {"count_result": {"Removed variables": 8}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_InlineStreamGuard_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_InlineStreamGuard_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 7}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_Metaprogramming_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_Metaprogramming_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_Synchronized_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_Synchronized_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/Dict_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/Dict_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/operators_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/operators_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libjitbackend_test.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libjitbackend_test.so", "details": {"count_result": {"Removed variables": 6}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/op_registration_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/op_registration_test", "details": {"count_result": {"Removed functions": 25, "Removed variables": 146}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/extension_backend_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/extension_backend_test", "details": {"count_result": {"Removed functions": 17, "Removed variables": 54}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_InlineDeviceGuard_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_InlineDeviceGuard_test", "details": {"count_result": {"Removed functions": 16, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/memory_format_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/memory_format_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/cpu_profiling_allocator_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/cpu_profiling_allocator_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/TCPStoreTest", "new": "/usr/lib64/python3.11/site-packages/torch/bin/TCPStoreTest", "details": {"count_result": {"Removed functions": 15, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/xla_tensor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/xla_tensor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_small_vector_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_small_vector_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/broadcast_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/broadcast_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_cpp_rpc", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_cpp_rpc", "details": {"count_result": {"Removed functions": 13, "Removed variables": 7}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libtorch_cpu.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libtorch_cpu.so", "details": {"count_result": {"Removed functions": 7390, "Removed variables": 864}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_complex_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_complex_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/undefined_tensor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/undefined_tensor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_accumulate_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_accumulate_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/math_kernel_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/math_kernel_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/MaybeOwned_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/MaybeOwned_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_ConstexprCrc_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_ConstexprCrc_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_tempfile_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_tempfile_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/dispatch_key_set_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/dispatch_key_set_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_flags_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_flags_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 2}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_dist_autograd", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_dist_autograd", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/basic", "new": "/usr/lib64/python3.11/site-packages/torch/test/basic", "details": {"count_result": {"Removed functions": 13, "Removed variables": 7}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libtorch_python.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libtorch_python.so", "details": {"count_result": {"Removed functions": 3672, "Removed variables": 990}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_LeftRight_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_LeftRight_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/CppSignature_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/CppSignature_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_lazy", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_lazy", "details": {"count_result": {"Removed functions": 17, "Removed variables": 10}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/legacy_vmap_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/legacy_vmap_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/List_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/List_test", "details": {"count_result": {"Removed functions": 17, "Removed variables": 10}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_Bitset_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_Bitset_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/scalar_tensor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/scalar_tensor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libc10.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libc10.so", "details": {"count_result": {"Removed functions": 51, "Removed variables": 7}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/ivalue_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/ivalue_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 7}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeIndex_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeIndex_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/kernel_lambda_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/kernel_lambda_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 35}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeTraits_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeTraits_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/NamedTensor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/NamedTensor_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 6}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_SymInt_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_SymInt_test", "details": {"count_result": {"Removed functions": 14, "Removed variables": 28}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/packedtensoraccessor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/packedtensoraccessor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_registry_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_registry_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/lazy_tensor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/lazy_tensor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/atest", "new": "/usr/lib64/python3.11/site-packages/torch/test/atest", "details": {"count_result": {"Removed functions": 13, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_edge_op_registration", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_edge_op_registration", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/quantized_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/quantized_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_StreamGuard_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_StreamGuard_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/StorageUtils_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/StorageUtils_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/stride_properties_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/stride_properties_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/scalar_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/scalar_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_bfloat16_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_bfloat16_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/kernel_function_legacy_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/kernel_function_legacy_test", "details": {"count_result": {"Removed functions": 18, "Removed variables": 47}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_ThreadLocal_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_ThreadLocal_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_DeviceGuard_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_DeviceGuard_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/backend_fallback_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/backend_fallback_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_optional_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_optional_test", "details": {"count_result": {"Removed functions": 16, "Removed variables": 98}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_bit_cast_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_bit_cast_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/mobile_memory_cleanup", "new": "/usr/lib64/python3.11/site-packages/torch/test/mobile_memory_cleanup", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_typeid_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_typeid_test", "details": {"count_result": {"Removed functions": 14, "Removed variables": 2}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/Dimname_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/Dimname_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeList_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_TypeList_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/op_allowlist_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/op_allowlist_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/type_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/type_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_irange_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_irange_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libtorchbind_test.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libtorchbind_test.so", "details": {"count_result": {"Removed functions": 1, "Removed variables": 26}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_jit", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_jit", "details": {"count_result": {"Removed functions": 31, "Removed variables": 28}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/tensor_iterator_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/tensor_iterator_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/weakref_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/weakref_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/half_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/half_test", "details": {"count_result": {"Removed functions": 14, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_intrusive_ptr_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_intrusive_ptr_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/memory_overlapping_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/memory_overlapping_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_DispatchKeySet_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_DispatchKeySet_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/apply_utils_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/apply_utils_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/FileStoreTest", "new": "/usr/lib64/python3.11/site-packages/torch/bin/FileStoreTest", "details": {"count_result": {"Removed functions": 14, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/test_parallel", "new": "/usr/lib64/python3.11/site-packages/torch/test/test_parallel", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_tensorexpr", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_tensorexpr", "details": {"count_result": {"Removed functions": 30, "Removed variables": 38}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/test_api", "new": "/usr/lib64/python3.11/site-packages/torch/bin/test_api", "details": {"count_result": {"Removed functions": 86, "Removed variables": 228}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/make_boxed_from_unboxed_functor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/make_boxed_from_unboxed_functor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 35}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/reportMemoryUsage_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/reportMemoryUsage_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_complex_math_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_complex_math_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_CompileTimeFunctionPointer_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_CompileTimeFunctionPointer_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/operator_name_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/operator_name_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/torch_shm_manager", "new": "/usr/lib64/python3.11/site-packages/torch/bin/torch_shm_manager", "details": {"count_result": {"Removed functions": 2, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_logging_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_logging_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_SizesAndStrides_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_SizesAndStrides_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/kernel_function_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/kernel_function_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 35}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_DeadlockDetection_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_DeadlockDetection_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/cpu_generator_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/cpu_generator_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/reduce_ops_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/reduce_ops_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_exception_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_exception_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/wrapdim_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/wrapdim_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/kernel_stackbased_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/kernel_stackbased_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_Device_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_Device_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/KernelFunction_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/KernelFunction_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/inline_container_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/inline_container_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_string_view_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_string_view_test", "details": {"count_result": {"Removed functions": 20, "Removed variables": 18}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/pow_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/pow_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 4}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/kernel_lambda_legacy_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/kernel_lambda_legacy_test", "details": {"count_result": {"Removed functions": 14, "Removed variables": 35}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_ordered_preserving_dict_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_ordered_preserving_dict_test", "details": {"count_result": {"Removed functions": 13, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/lib/libbackend_with_compiler.so", "new": "/usr/lib64/python3.11/site-packages/torch/lib/libbackend_with_compiler.so", "details": {"count_result": {"Removed functions": 5, "Removed variables": 6}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/bin/HashStoreTest", "new": "/usr/lib64/python3.11/site-packages/torch/bin/HashStoreTest", "details": {"count_result": {"Removed functions": 14, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/dlconvertor_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/dlconvertor_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/type_ptr_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/type_ptr_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}, {"old": "/usr/lib64/python3.11/site-packages/functorch/_C.cpython-311-aarch64-linux-gnu.so", "new": "/usr/lib64/python3.11/site-packages/functorch/_C.cpython-311-aarch64-linux-gnu.so", "details": {"count_result": {"Removed functions": 1, "Removed variables": 3}}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_ssize_test", "new": "/usr/lib64/python3.11/site-packages/torch/test/c10_ssize_test", "details": {"count_result": {"Removed functions": 12, "Removed variables": 1}}}], "less": [{"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_context_test", "new": "", "details": {"effect_rpm": []}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/variant_test", "new": "", "details": {"effect_rpm": []}}, {"old": "/usr/lib64/python3.11/site-packages/torch/test/c10_either_test", "new": "", "details": {"effect_rpm": []}}]}}}, "diff_num": 1}, "less": {"less_details": {}, "less_num": 0}, "more": {"more_details": {}, "more_num": 0}}, "pr_link": "https://gitcode.com/src-openeuler/pytorch/pull/124", "pr_changelog": "* Fri Jul 11 2025 Xiaoshuang Wang <1790571317@qq.com> - 2.7.0-1\n- upgrade to 2.7.0\n\n* Fri Jul 18 2025 Dongxing Wang <dongxing.wang_a@thundersoft.com> - 2.1.2-6\n- Backport: Make PyTorch compilable against upcoming Numpy-2.0\n\n* Wed Mar 5 2025 zhangzikang <zhangzikang@kylinos.cn> - 2.1.2-5\n- Sync from 24.03sp1: Fix build error for loongarch64\n\n* Wed Mar 5 2025 wangxiaomeng <wangxiaomeng@kylinos.cn> - 2.1.2-4\n- Sync from 24.03sp1: Fix CVE-2024-31584\n\n* Wed Jul 17 2024 Dingli Zhang <dingli@iscas.ac.cn> - 2.1.2-3"}