Forward:一个用于在NVIDIA GPU上进行高性能深度学习推理的库 （987个子文件） 
VS2019.bat 371B VS2017.bat 227B meson.build 552B gtest.cc 213KB gtest-death-test.cc 57KB gtest-port.cc 43KB gtest-printers.cc 15KB gtest-filepath.cc 14KB gtest-typed-test.cc 4KB gtest-test-part.cc 4KB gtest-all.cc 2KB gtest_main.cc 2KB setup.cfg 312B CHANGES 6KB .clang-format 315B .clang-tidy 736B internal_utils.cmake 13KB pybind11Tools.cmake 9KB FindPythonLibsNew.cmake 8KB FindTensorRT.cmake 3KB FindEigen3.cmake 3KB FindCatch.cmake 2KB CONTRIBUTORS 1KB fused_multihead_attention_v2_int8_192_64_kernel.sm75.cpp 1.45MB fused_multihead_attention_v2_int8_128_64_kernel.sm72.cpp 1.44MB fused_multihead_attention_v2_int8_256_64_kernel.sm72.cpp 1.43MB fused_multihead_attention_v2_int8_384_64_kernel.sm72.cpp 1.4MB fused_multihead_attention_v2_int8_384_64_kernel.sm75.cpp 1.34MB fused_multihead_attention_v2_int8_384_64_kernel.sm80.cpp 1.23MB fused_multihead_attention_v2_int8_192_64_kernel.sm72.cpp 1.14MB fused_multihead_attention_v2_int8_128_64_kernel.sm75.cpp 1.13MB fused_multihead_attention_v2_int8_192_64_kernel.sm80.cpp 1.07MB fused_multihead_attention_v2_int8_128_64_kernel.sm80.cpp 1.06MB fused_multihead_attention_v2_int8_256_64_kernel.sm75.cpp 1022KB fused_multihead_attention_v2_int8_256_64_kernel.sm80.cpp 956KB fused_multihead_attention_v2_fp16_128_64_kernel.sm75.cpp 481KB fused_multihead_attention_v2_fp16_128_64_kernel.sm80.cpp 444KB fused_multihead_attention_v2_fp16_384_64_kernel.sm80.cpp 439KB fused_multihead_attention_v2_fp16_256_64_kernel.sm75.cpp 423KB fused_multihead_attention_int8_128_64_kernel.sm75.cpp 415KB fused_multihead_attention_v2_fp16_256_64_kernel.sm80.cpp 397KB fused_multihead_attention_int8_128_64_kernel.sm80.cpp 377KB fused_multihead_attention_v2_fp16_384_64_kernel.sm75.cpp 344KB fused_multihead_attention_int8_384_64_kernel.sm80.cpp 314KB fused_multihead_attention_fp16_128_64_kernel.sm75.cpp 312KB fused_multihead_attention_int8_384_64_kernel.sm75.cpp 310KB fused_multihead_attention_fp16_128_64_kernel.sm80.cpp 263KB fused_multihead_attention_fp16_384_64_kernel.sm75.cpp 209KB fused_multihead_attention_v2_fp16_96_64_kernel.sm75.cpp 208KB fused_multihead_attention_v2_fp16_96_64_kernel.sm80.cpp 203KB fused_multihead_attention_fp16_384_64_kernel.sm80.cpp 191KB fused_multihead_attention_fp16_96_64_kernel.sm75.cpp 176KB fused_multihead_attention_fp16_96_64_kernel.sm80.cpp 171KB fused_multihead_attention_v2_fp16_64_64_kernel.sm80.cpp 120KB fused_multihead_attention_v2_fp16_64_64_kernel.sm75.cpp 118KB fused_multihead_attention_fp16_64_64_kernel.sm75.cpp 105KB fused_multihead_attention_fp16_64_64_kernel.sm80.cpp 103KB qkv_to_context_plugin.cpp 33KB skip_layer_norm_plugin.cpp 31KB test_methods_and_attributes.cpp 23KB emb_layer_norm_plugin.cpp 20KB normalization_plugin.cpp 18KB test_virtual_functions.cpp 17KB test_class.cpp 17KB test_eigen.cpp 16KB test_smart_ptr.cpp 16KB test_numpy_dtypes.cpp 16KB test_factory_constructors.cpp 16KB wcwidth.cpp 14KB fold_floor_divide.cpp 13KB embedding_bag_plugin.cpp 13KB trt_fwd_engine.cpp 13KB grid_sampler_plugin.cpp 13KB index_plugin.cpp 13KB trt_fwd_builder.cpp 13KB upsample_bilinear_2d.cpp 13KB test_numpy_array.cpp 12KB constant_pad_plugin.cpp 12KB adaptive_lin_plugin.cpp 12KB test_sequences_and_iterators.cpp 12KB adaptive_pooling_plugin.cpp 12KB reduce_plugin.cpp 11KB test_stl.cpp 11KB split_plugin.cpp 11KB fuse_transformer_encoder.cpp 11KB norm_plugin.cpp 10KB reflection_padding_plugin.cpp 10KB trt_keras_parser.cpp 10KB test_interpreter.cpp 10KB torch_engine.cpp 10KB trt_creator_manager.cpp 9KB cast_plugin.cpp 9KB torch_module_parser.cpp 9KB test_copy_move.cpp 9KB gelu_plugin.cpp 9KB tf_graph_parser.cpp 9KB test_pytypes.cpp 9KB test_builtin_casters.cpp 9KB test_multiple_inheritance.cpp 9KB keras_cpp_api.cpp 9KB共 987 条
- 1
- 2
- 3
- 4
- 5
- 6
- 10
资源评论
普通网友
- 粉丝: 30
- 资源: 4570
最新资源
资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！
点击此处反馈
