TensorRT：TensorRT是一个C ++库，用于在NVIDIA GPU和深度学习加速器上进行高性能推理
5星 · 超过95%的资源 需积分: 27 158 浏览量
2021-02-05
09:38:16
上传
评论
收藏 4.16MB ZIP 举报 
TensorRT：TensorRT是一个C ++库，用于在NVIDIA GPU和深度学习加速器上进行高性能推理 （972个子文件） 
getopt.c 17KB setup.cfg 83B setup.cfg 28B setup.cfg 28B .clang-format 2KB protobuf.cmake 10KB find_library_create_target.cmake 1KB zlib.cmake 914B set_ifndef.cmake 748B .coveragerc 210B fused_multihead_attention_v2_int8_192_64_kernel.sm75.cpp 1.43MB fused_multihead_attention_v2_int8_128_64_kernel.sm72.cpp 1.42MB fused_multihead_attention_v2_int8_256_64_kernel.sm72.cpp 1.41MB fused_multihead_attention_v2_int8_384_64_kernel.sm72.cpp 1.39MB fused_multihead_attention_v2_int8_384_64_kernel.sm75.cpp 1.32MB fused_multihead_attention_v2_int8_384_64_kernel.sm80.cpp 1.22MB fused_multihead_attention_v2_int8_192_64_kernel.sm72.cpp 1.13MB fused_multihead_attention_v2_int8_128_64_kernel.sm75.cpp 1.12MB fused_multihead_attention_v2_int8_192_64_kernel.sm80.cpp 1.06MB fused_multihead_attention_v2_int8_128_64_kernel.sm80.cpp 1.04MB fused_multihead_attention_v2_int8_256_64_kernel.sm75.cpp 1009KB fused_multihead_attention_v2_int8_256_64_kernel.sm80.cpp 943KB fused_multihead_attention_v2_fp16_128_64_kernel.sm75.cpp 475KB fused_multihead_attention_v2_fp16_128_64_kernel.sm80.cpp 438KB fused_multihead_attention_v2_fp16_384_64_kernel.sm80.cpp 433KB fused_multihead_attention_v2_fp16_256_64_kernel.sm75.cpp 418KB fused_multihead_attention_int8_128_64_kernel.sm75.cpp 412KB fused_multihead_attention_v2_fp16_256_64_kernel.sm80.cpp 391KB fused_multihead_attention_int8_128_64_kernel.sm80.cpp 375KB fused_multihead_attention_v2_fp16_384_64_kernel.sm75.cpp 339KB fused_multihead_attention_int8_384_64_kernel.sm80.cpp 312KB fused_multihead_attention_fp16_128_64_kernel.sm75.cpp 310KB fused_multihead_attention_int8_384_64_kernel.sm75.cpp 308KB fused_multihead_attention_fp16_128_64_kernel.sm80.cpp 262KB fused_multihead_attention_fp16_384_64_kernel.sm75.cpp 208KB fused_multihead_attention_v2_fp16_96_64_kernel.sm75.cpp 205KB fused_multihead_attention_v2_fp16_96_64_kernel.sm80.cpp 201KB fused_multihead_attention_fp16_384_64_kernel.sm80.cpp 190KB fused_multihead_attention_fp16_96_64_kernel.sm75.cpp 173KB fused_multihead_attention_fp16_96_64_kernel.sm80.cpp 169KB fused_multihead_attention_v2_fp16_64_64_kernel.sm80.cpp 119KB fused_multihead_attention_v2_fp16_64_64_kernel.sm75.cpp 116KB fused_multihead_attention_fp16_64_64_kernel.sm75.cpp 103KB fused_multihead_attention_fp16_64_64_kernel.sm80.cpp 102KB sampleNMT.cpp 60KB sampleOptions.cpp 55KB sampleCharRNN.cpp 42KB qkvToContextPlugin.cpp 33KB sampleINT8API.cpp 31KB skipLayerNormPlugin.cpp 29KB sampleMovieLensMPS.cpp 28KB caffeParser.cpp 28KB fcPlugin.cpp 27KB sampleUffFasterRCNN.cpp 26KB sampleAlgorithmSelector.cpp 26KB sampleUffPluginV2Ext.cpp 25KB sampleEngines.cpp 24KB sampleMovieLens.cpp 23KB sampleUffMaskRCNN.cpp 23KB sampleReformatFreeIO.cpp 22KB batchedNMSPlugin.cpp 21KB embLayerNormPlugin.cpp 20KB sampleFasterRCNN.cpp 20KB sampleDynamicReshape.cpp 19KB sampleINT8.cpp 19KB sampleMLP.cpp 19KB embLayerNormVarSeqlenPlugin.cpp 18KB gridAnchorPlugin.cpp 17KB sampleInference.cpp 17KB sampleMNISTAPI.cpp 17KB nvFasterRCNNPlugin.cpp 17KB priorBoxPlugin.cpp 17KB sampleUffSSD.cpp 16KB multilevelProposeROIPlugin.cpp 16KB sampleSSD.cpp 15KB samplePlugin.cpp 15KB instanceNormalizationPlugin.cpp 15KB proposalPlugin.cpp 14KB sampleMNIST.cpp 14KB regionPlugin.cpp 14KB nmsPlugin.cpp 13KB sampleReporting.cpp 13KB sampleUffMNIST.cpp 12KB sampleOnnxMnistCoordConvAC.cpp 12KB caffeWeightFactory.cpp 12KB sampleOnnxMNIST.cpp 12KB proposalLayerPlugin.cpp 11KB groupNormalizationPlugin.cpp 11KB skipLayerNormInt8InterleavedPlugin.cpp 11KB generateDetectionPlugin.cpp 11KB qkvToContextInt8InterleavedPlugin.cpp 11KB normalizePlugin.cpp 10KB flattenConcat.cpp 10KB detectionLayerPlugin.cpp 9KB sampleGoogleNet.cpp 9KB cropAndResizePlugin.cpp 9KB geluPlugin.cpp 9KB multilevelCropAndResizePlugin.cpp 9KB pyramidROIAlignPlugin.cpp 8KB getOptions.cpp 8KB共 972 条
- 1
- 2
- 3
- 4
- 5
- 6
- 10
资源评论
weixin_422105462021-08-12用户下载后在一定时间内未进行评价，系统默认好评。
