MANIFEST.in
pyproject.toml
setup.py
build_tools/VERSION.txt
build_tools/__init__.py
build_tools/build_ext.py
build_tools/jax.py
build_tools/pytorch.py
build_tools/te_version.py
build_tools/utils.py
build_tools/__pycache__/__init__.cpython-310.pyc
build_tools/__pycache__/build_ext.cpython-310.pyc
build_tools/__pycache__/pytorch.cpython-310.pyc
build_tools/__pycache__/te_version.cpython-310.pyc
build_tools/__pycache__/utils.cpython-310.pyc
build_tools/wheel_utils/Dockerfile.aarch
build_tools/wheel_utils/Dockerfile.x86
build_tools/wheel_utils/build_wheels.sh
build_tools/wheel_utils/launch_aarch.sh
build_tools/wheel_utils/launch_x86.sh
common_headers/common/common.h
common_headers/common/cudnn_utils.h
common_headers/common/nvtx.h
common_headers/common/utils.cuh
common_headers/common/activation/activation_template.h
common_headers/common/comm_gemm_overlap/userbuffers/ipcsocket.h
common_headers/common/comm_gemm_overlap/userbuffers/userbuffers.h
common_headers/common/fused_attn/fused_attn_f16_arbitrary_seqlen.h
common_headers/common/fused_attn/fused_attn_f16_max512_seqlen.h
common_headers/common/fused_attn/fused_attn_fp8.h
common_headers/common/fused_attn/utils.h
common_headers/common/fused_router/utils.h
common_headers/common/gemm/config.h
common_headers/common/gemm/cutlass_grouped_gemm.cuh
common_headers/common/include/transformer_engine/activation.h
common_headers/common/include/transformer_engine/cast.h
common_headers/common/include/transformer_engine/cast_transpose_noop.h
common_headers/common/include/transformer_engine/comm_gemm.h
common_headers/common/include/transformer_engine/comm_gemm_overlap.h
common_headers/common/include/transformer_engine/cudnn.h
common_headers/common/include/transformer_engine/dropout.h
common_headers/common/include/transformer_engine/fused_attn.h
common_headers/common/include/transformer_engine/fused_rope.h
common_headers/common/include/transformer_engine/fused_router.h
common_headers/common/include/transformer_engine/gemm.h
common_headers/common/include/transformer_engine/hadamard_transform.h
common_headers/common/include/transformer_engine/multi_stream.h
common_headers/common/include/transformer_engine/multi_tensor.h
common_headers/common/include/transformer_engine/normalization.h
common_headers/common/include/transformer_engine/padding.h
common_headers/common/include/transformer_engine/permutation.h
common_headers/common/include/transformer_engine/recipe.h
common_headers/common/include/transformer_engine/softmax.h
common_headers/common/include/transformer_engine/swizzle.h
common_headers/common/include/transformer_engine/transformer_engine.h
common_headers/common/include/transformer_engine/transpose.h
common_headers/common/multi_tensor/multi_tensor_apply.cuh
common_headers/common/normalization/common.h
common_headers/common/normalization/kernel_traits.h
common_headers/common/normalization/layernorm/ln_bwd_kernels.cuh
common_headers/common/normalization/layernorm/ln_fwd_kernels.cuh
common_headers/common/normalization/rmsnorm/rmsnorm_bwd_kernels.cuh
common_headers/common/normalization/rmsnorm/rmsnorm_fwd_kernels.cuh
common_headers/common/nvshmem_api/nvshmem_waitkernel.h
common_headers/common/recipe/recipe_common.cuh
common_headers/common/transpose/cast_transpose.h
common_headers/common/util/cast_gated_kernels.cuh
common_headers/common/util/cast_kernels.cuh
common_headers/common/util/cuda_driver.h
common_headers/common/util/cuda_nvml.h
common_headers/common/util/cuda_runtime.h
common_headers/common/util/dequantize_kernels.cuh
common_headers/common/util/handle_manager.h
common_headers/common/util/logging.h
common_headers/common/util/math.h
common_headers/common/util/multi_stream.h
common_headers/common/util/nvfp4_transpose.cuh
common_headers/common/util/ptx.cuh
common_headers/common/util/pybind_helper.h
common_headers/common/util/rtc.h
common_headers/common/util/shared_lib_wrapper.h
common_headers/common/util/string.h
common_headers/common/util/system.h
common_headers/common/util/vectorized_pointwise.h
csrc/common.cpp
csrc/common.h
csrc/extensions.h
csrc/pybind.h
csrc/quantizer.cpp
csrc/type_converters.cpp
csrc/util.cpp
csrc/util.h
csrc/extensions/activation.cpp
csrc/extensions/apply_rope.cpp
csrc/extensions/attention.cpp
csrc/extensions/bias.cpp
csrc/extensions/cast.cpp
csrc/extensions/comm_gemm_overlap.cpp
csrc/extensions/dropout.cpp
csrc/extensions/fp8_block_scaling_partial_cast.cpp
csrc/extensions/gemm.cpp
csrc/extensions/misc.cpp
csrc/extensions/normalization.cpp
csrc/extensions/nvshmem_comm.cpp
csrc/extensions/padding.cpp
csrc/extensions/permutation.cpp
csrc/extensions/pybind.cpp
csrc/extensions/recipe.cpp
csrc/extensions/router.cpp
csrc/extensions/softmax.cpp
csrc/extensions/transpose.cpp
csrc/extensions/multi_tensor/adam.cpp
csrc/extensions/multi_tensor/compute_scale.cpp
csrc/extensions/multi_tensor/l2norm.cpp
csrc/extensions/multi_tensor/scale.cpp
csrc/extensions/multi_tensor/sgd.cpp
transformer_engine_torch.egg-info/PKG-INFO
transformer_engine_torch.egg-info/SOURCES.txt
transformer_engine_torch.egg-info/dependency_links.txt
transformer_engine_torch.egg-info/requires.txt
transformer_engine_torch.egg-info/top_level.txt