| .. |
|
contextFusedMultiHeadAttention
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
cutlass_kernels
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
decoderMaskedMultiheadAttention
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
onlineSoftmaxBeamsearchKernels
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
weightOnlyBatchedGemv
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
banBadWords.cu
|
Update code
|
2023-09-28 09:00:05 -07:00 |
|
banBadWords.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
banRepeatNgram.cu
|
Update code
|
2023-09-28 09:00:05 -07:00 |
|
banRepeatNgram.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
beamSearchPenaltyKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
beamSearchPenaltyKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
beamSearchTopkKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
beamSearchTopkKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
CMakeLists.txt
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
customAllReduceKernels.cu
|
Updates for release/0.5.0
|
2023-10-15 21:26:20 +08:00 |
|
customAllReduceKernels.h
|
Updates for release/0.5.0
|
2023-10-15 21:26:20 +08:00 |
|
decoderMaskedMultiheadAttention.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
decoderMaskedMultiheadAttention.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
decoderMaskedMultiheadAttentionUtils.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
decodingKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
decodingKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
gptKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
gptKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
kvCacheUtils.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
layernormKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
layernormKernels.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
lookupKernels.cu
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
lookupKernels.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
onlineSoftmaxBeamsearchKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
onlineSoftmaxBeamsearchKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
penaltyTypes.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
preQuantScaleKernel.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
preQuantScaleKernel.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
quantization.cu
|
Update code
|
2023-09-28 09:00:05 -07:00 |
|
quantization.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
rmsnormKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
rmsnormKernels.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
samplingPenaltyKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
samplingPenaltyKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
samplingTopKKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
samplingTopKKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
samplingTopPKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
samplingTopPKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
stopCriteriaKernels.cu
|
Update
|
2023-10-10 23:22:17 -07:00 |
|
stopCriteriaKernels.h
|
Initial commit
|
2023-09-20 00:29:41 -07:00 |
|
unfusedAttentionKernels_2.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
unfusedAttentionKernels.cu
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
|
unfusedAttentionKernels.h
|
Update TensorRT-LLM (#506)
|
2023-11-30 16:46:22 +08:00 |
587d063e6d