apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
파일 탐색기
최종 버전 다운로드 (.zip)- bug_report.md
- __init__.py
- bottleneck.py
- halo_exchangers.py
- test.py
- __init__.py
- clip_grad.py
- __init__.py
- conv_bias_relu.py
- bottleneck.cpp
- conv_bias_relu.cpp
- cudnn_gbn.cpp
- norm_sample.cpp
- norm_sample.h
- focal_loss_cuda.cpp
- focal_loss_cuda_kernel.cu
- group_norm_nhwc.cpp
- group_norm_nhwc.h
- group_norm_nhwc_bwd_one_pass.h
- group_norm_nhwc_bwd_one_pass_kernel.cuh
- group_norm_nhwc_bwd_two_pass.cu
- group_norm_nhwc_fwd_one_pass.h
- group_norm_nhwc_fwd_one_pass_kernel.cuh
- group_norm_nhwc_fwd_two_pass.cu
- group_norm_nhwc_one_pass_10.cu
- group_norm_nhwc_one_pass_112.cu
- group_norm_nhwc_one_pass_12.cu
- group_norm_nhwc_one_pass_120.cu
- group_norm_nhwc_one_pass_128.cu
- group_norm_nhwc_one_pass_14.cu
- group_norm_nhwc_one_pass_16.cu
- group_norm_nhwc_one_pass_160.cu
- group_norm_nhwc_one_pass_20.cu
- group_norm_nhwc_one_pass_24.cu
- group_norm_nhwc_one_pass_26.cu
- group_norm_nhwc_one_pass_28.cu
- group_norm_nhwc_one_pass_30.cu
- group_norm_nhwc_one_pass_32.cu
- group_norm_nhwc_one_pass_4.cu
- group_norm_nhwc_one_pass_40.cu
- group_norm_nhwc_one_pass_42.cu
- group_norm_nhwc_one_pass_48.cu
- group_norm_nhwc_one_pass_56.cu
- group_norm_nhwc_one_pass_60.cu
- group_norm_nhwc_one_pass_64.cu
- group_norm_nhwc_one_pass_70.cu
- group_norm_nhwc_one_pass_8.cu
- group_norm_nhwc_one_pass_80.cu
- group_norm_nhwc_one_pass_84.cu
- group_norm_nhwc_one_pass_96.cu
- group_norm_nhwc_one_pass_98.cu
- group_norm_nhwc_op.cpp
- macros.h
- traits.h
- generate_gn_cuda_inst.py
- gn.cpp
- gn.hpp
- gn_cuda.cu
- gn_cuda_host_template.cuh
- gn_cuda_inst_1024_1280.cu
- gn_cuda_inst_1024_1920.cu
- gn_cuda_inst_1024_320.cu
- gn_cuda_inst_1024_640.cu
- gn_cuda_inst_1024_960.cu
- gn_cuda_inst_256_1280.cu
- gn_cuda_inst_256_1920.cu
- gn_cuda_inst_256_2560.cu
- gn_cuda_inst_256_640.cu
- gn_cuda_inst_4096_320.cu
- gn_cuda_inst_4096_640.cu
- gn_cuda_inst_4096_960.cu
- gn_cuda_inst_64_1280.cu
- gn_cuda_inst_64_2560.cu
- gn_cuda_kernel.cuh
- gn_dispatch_hw_c.hpp
- gn_utils.cpp
- gn_utils.hpp
- batch_norm.cu
- batch_norm.h
- batch_norm_add_relu.cu
- batch_norm_add_relu.h
- cuda_utils.h
- interface.cpp
- ipc.cu
- nhwc_batch_norm_kernel.h
- index_mul_2d_cuda.cpp
- index_mul_2d_cuda_kernel.cu
- ln.h
- ln_api.cpp
- ln_bwd_kernels.cuh
- ln_bwd_semi_cuda_kernel.cu
- ln_fwd_cuda_kernel.cu
- ln_fwd_kernels.cuh
- ln_kernel_traits.h
- ln_utils.cuh
- NCCLAllocator.cpp
- nccl_p2p.cpp
- nccl_p2p_cuda.cu
- nccl_p2p_cuda.cuh
- nccl_version.cpp
- nccl_version_check.cu
- fused_adam_cuda.cpp
- fused_adam_cuda_kernel.cu
- fused_lamb_cuda.cpp
- fused_lamb_cuda_kernel.cu
- multi_tensor_distopt_adam.cpp
- multi_tensor_distopt_adam_kernel.cu
- multi_tensor_distopt_lamb.cpp
- multi_tensor_distopt_lamb_kernel.cu
- peer_memory.cpp
- peer_memory_cuda.cu
- peer_memory_cuda.cuh
- philox.cuh
- transducer_joint.cpp
- transducer_joint_kernel.cu
- transducer_loss.cpp
- transducer_loss_kernel.cu
- interface.cpp
- xentropy_kernel.cu
- cudnn-frontend
- __init__.py
- batch_norm.py
- benchmark_load.py
- benchmark_save.py
- example_load.py
- example_save.py
- allreduce.py
- cache.py
- change_cuda_allocator.py
- toy_ddp.py
- __init__.py
- focal_loss.py
- __init__.py
- group_norm.py
- __init__.py
- batch_norm.py
- __init__.py
- index_mul_2d.py
- __init__.py
- layer_norm.py
- __init__.py
- nccl_allocator.py
- README.md
- __init__.py
- _layer_norm_backward_kernels.py
- _layer_norm_config_ampere.py
- _layer_norm_config_hopper.py
- _layer_norm_forward_kernels.py
- _mha_kernel.py
- fused_adam_swa.py
- layer_norm.py
- mha.py
- README.md
- __init__.py
- distributed_fused_adam.py
- distributed_fused_lamb.py
- fp16_optimizer.py
- fused_adam.py
- fused_lamb.py
- fused_sgd.py
- __init__.py
- peer_halo_exchanger_1d.py
- peer_memory.py
- permutation_search_kernels.cu
- __init__.py
- call_permutation_search_kernels.py
- channel_swap.py
- exhaustive_search.py
- permutation_utilities.py
- ablation_studies.sh
- permutation_test.py
- README.md
- runtime_table.sh
- unstructured_study.sh
- checkpointing_test_part1.py
- checkpointing_test_part2.py
- checkpointing_test_reference.py
- test_permutation_application.py
- toy_problem.py
- __init__.py
- asp.py
- COPYRIGHT
- permutation_lib.py
- README.md
- sparse_masklib.py
- __init__.py
- test_bottleneck_module.py
- __init__.py
- test_clip_grad.py
- __init__.py
- test_conv_bias_relu.py
- __init__.py
- test_cudnn_gbn_with_two_gpus.py
- __init__.py
- test_focal_loss.py
- test_fused_dense.py
- __init__.py
- test_group_norm.py
- __init__.py
- test_index_mul_2d.py
- __init__.py
- test_fast_layer_norm.py
- test_fused_adam_swa.py
- test_openfold_mha.py
- test_sync_triton_auto_tune_cache_across_gpus.py
- __init__.py
- test_dist_adam.py
- test_distributed_fused_lamb.py
- __init__.py
- test_peer_halo_exchange_module.py
- __init__.py
- test_transducer_joint.py
- test_transducer_loss.py
- __init__.py
- test_label_smoothing.py
- __init__.py
- __init__.py
- _utils.py
- event.py
- graph.py
- scheduler.py
- wrapper.py
- __init__.py
- layer_norm.py
- __init__.py
- pre_grad_passes.py
- __init__.py
- backend.py
- config.py
- __init__.py
- _transducer_ref.py
- transducer.py
- __init__.py
- softmax_xentropy.py
- __init__.py
- __init__.py
- _ucc_util.py
- distributed_test_base.py
- __init__.py
- fused_dense.py
- __init__.py
- mlp.py
- __init__.py
- multi_tensor_apply.py
- __init__.py
- fused_layer_norm.py
- __init__.py
- fused_adagrad.py
- fused_adam.py
- fused_lamb.py
- fused_mixed_precision_lamb.py
- fused_novograd.py
- fused_sgd.py
- __init__.py
- _autocast_utils.py
- fused_rotary_positional_embedding.cpp
- fused_rotary_positional_embedding.h
- fused_rotary_positional_embedding_cuda.cu
- fused_weight_gradient_dense.cpp
- fused_weight_gradient_dense_16bit_prec_cuda.cu
- fused_weight_gradient_dense_cuda.cu
- generic_scaled_masked_softmax.cpp
- generic_scaled_masked_softmax.h
- generic_scaled_masked_softmax_cuda.cu
- scaled_masked_softmax.cpp
- scaled_masked_softmax.h
- scaled_masked_softmax_cuda.cu
- scaled_softmax.cpp
- scaled_softmax_cuda.cu
- scaled_upper_triang_masked_softmax.cpp
- scaled_upper_triang_masked_softmax.h
- scaled_upper_triang_masked_softmax_cuda.cu
- amp_C_frontend.cpp
- flatten_unflatten.cpp
- fused_dense.cpp
- fused_dense_cuda.cu
- layer_norm_cuda.cpp
- layer_norm_cuda_kernel.cu
- mlp.cpp
- mlp_cuda.cu
- multi_tensor_adagrad.cu
- multi_tensor_adam.cu
- multi_tensor_apply.cuh
- multi_tensor_axpby_kernel.cu
- multi_tensor_l2norm_kernel.cu
- multi_tensor_l2norm_kernel_mp.cu
- multi_tensor_l2norm_scale_kernel.cu
- multi_tensor_lamb.cu
- multi_tensor_lamb_mp.cu
- multi_tensor_lamb_stage_1.cu
- multi_tensor_lamb_stage_2.cu
- multi_tensor_novograd.cu
- multi_tensor_scale_kernel.cu
- multi_tensor_sgd_kernel.cu
- static_switch.h
- syncbn.cpp
- type_shim.h
- update_scale_hysteresis.cu
- welford.cu
- pytorch_theme.css
- nv-pytorch2.png
- layout.html
- conf.py
- index.rst
- layernorm.rst
- optimizers.rst
- Makefile
- main_amp.py
- README.md
- Dockerfile
- README.md
- main_amp.py
- README.md
- distributed_data_parallel.py
- README.md
- run.sh
- README.md
- amp_master_params.py
- compare.py
- run.sh
- ddp_race_condition_test.py
- run_race_test.sh
- python_single_gpu_unit_test.py
- single_gpu_unit_test.py
- test_batchnorm1d.py
- test_groups.py
- two_gpu_test_different_batch_size.py
- two_gpu_unit_test.py
- unit_test.sh
- run.sh
- test_fused_layer_norm.py
- test_mlp.py
- __init__.py
- test_adam.py
- test_fused_novograd.py
- test_fused_optimizer.py
- test_lamb.py
- run_test.py
- compare.py
- main_amp.py
- run_test.sh
- run.sh
- run.sh
- .clang-format
- .git-blame-ignore-revs
- .gitignore
- .gitmodules
- .nojekyll
- .pre-commit-config.yaml
- LICENSE
- pyproject.toml
- README.md
- requirements.txt
- requirements_dev.txt
- setup.py
// repository documentation
Was this content helpful?
(0 ratings)