| .. |
|
beamSearchKernels
|
|
|
|
causalConv1d
|
|
|
|
communicationKernels
|
[TRTLLM-10126][feat] Increase topk upper limit to 22 for NVLinkOneSid… (#10229)
|
2025-12-27 22:48:10 +08:00 |
|
contextFusedMultiHeadAttention
|
[TRTLLM-9805][feat] Skip Softmax Attention. (#9821)
|
2025-12-21 02:52:42 -05:00 |
|
cuteDslKernels
|
|
|
|
cutlass_kernels
|
[https://nvbugs/5726962][feat] Apply fusion for W4AFP8_AWQ MoE (#9838)
|
2026-01-06 10:16:41 +08:00 |
|
decoderMaskedMultiheadAttention
|
[TRTLLM-10022][feat] Add hopper xqa decode support for skip softmax attention (#10264)
|
2026-01-11 19:26:10 -05:00 |
|
dsv3MinLatencyKernels
|
|
|
|
flashMLA
|
|
|
|
fusedLayernormKernels
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
groupRmsNormKernels
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
internal_cutlass_kernels
|
[None][chore] Update internal_cutlass_kernels artifacts (#9992)
|
2025-12-15 21:15:25 -08:00 |
|
llama4MinLatencyKernels
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
lora
|
|
|
|
moeLoadBalance
|
|
|
|
selectiveScan
|
|
|
|
speculativeDecoding
|
|
|
|
tinygemm2
|
[None][chore] Update tinygemm kernel name (#10248)
|
2025-12-24 02:33:25 -05:00 |
|
trtllmGenKernels
|
[https://nvbugs/5503479][fix] update trtllm-gen kernels to address few bugs (#10089)
|
2025-12-22 04:45:33 -05:00 |
|
unfusedAttentionKernels
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
userbuffers
|
|
|
|
weightOnlyBatchedGemv
|
[None][feat] sm100 weight-only kernel (#10190)
|
2026-01-05 09:44:36 +08:00 |
|
attentionMask.cu
|
|
|
|
attentionMask.h
|
|
|
|
banBadWords.cu
|
|
|
|
banBadWords.h
|
|
|
|
banRepeatNgram.cu
|
|
|
|
banRepeatNgram.h
|
|
|
|
beamSearchKernels.cu
|
|
|
|
beamSearchKernels.h
|
|
|
|
buildRelativeAttentionBiasKernel.cu
|
|
|
|
buildRelativeAttentionBiasKernel.h
|
|
|
|
CMakeLists.txt
|
|
|
|
cudaAsyncOps.cuh
|
|
|
|
cumsumLastDim.cu
|
|
|
|
cumsumLastDim.h
|
|
|
|
customAllReduceKernels.cu
|
|
|
|
customAllReduceKernels.h
|
|
|
|
customMoeRoutingKernels.cu
|
|
|
|
customMoeRoutingKernels.h
|
|
|
|
decoderMaskedMultiheadAttention.cu
|
|
|
|
decoderMaskedMultiheadAttention.h
|
|
|
|
decoderMaskedMultiheadAttentionUtils.h
|
|
|
|
decodingCommon.cu
|
|
|
|
decodingKernels.cu
|
|
|
|
decodingKernels.h
|
|
|
|
delayStream.cu
|
|
|
|
delayStream.h
|
|
|
|
doraScaling.cu
|
|
|
|
doraScaling.h
|
|
|
|
fmhaDispatcher.cpp
|
[TRTLLM-9805][feat] Skip Softmax Attention. (#9821)
|
2025-12-21 02:52:42 -05:00 |
|
fmhaDispatcher.h
|
|
|
|
fusedMoeCommKernels.cu
|
|
|
|
fusedMoeCommKernels.h
|
|
|
|
fusedQKNormRopeKernel.cu
|
|
|
|
fusedQKNormRopeKernel.h
|
|
|
|
gptKernels.cu
|
|
|
|
gptKernels.h
|
|
|
|
groupGemm.cu
|
|
|
|
groupGemm.h
|
|
|
|
helixAllToAll.cu
|
[TRTLLM-9493][feat] Custom AllToAll for helix parallelism (#9986)
|
2025-12-23 18:14:30 -08:00 |
|
helixAllToAll.h
|
[TRTLLM-9493][feat] Custom AllToAll for helix parallelism (#9986)
|
2025-12-23 18:14:30 -08:00 |
|
helixKernels.cu
|
|
|
|
helixKernels.h
|
|
|
|
indexerKCacheScatter.cu
|
|
|
|
IndexerKCacheScatter.h
|
|
|
|
indexerTopK.cu
|
[https://nvbugs/5720357][fix] Fix indice offset overflow in custom Top-K kernel and corresponding UT case (#10027)
|
2025-12-19 14:58:01 -05:00 |
|
IndexerTopK.h
|
|
|
|
kvCachePartialCopy.cu
|
|
|
|
kvCacheUtils.h
|
|
|
|
layernormKernels.cu
|
|
|
|
layernormKernels.h
|
|
|
|
ll128Proto.cuh
|
|
|
|
logitsBitmask.cu
|
|
|
|
logitsBitmask.h
|
|
|
|
lookupKernels.cu
|
|
|
|
lookupKernels.h
|
|
|
|
lruKernel.cu
|
|
|
|
lruKernel.h
|
|
|
|
mambaConv1dKernels.cu
|
|
|
|
mambaConv1dKernels.h
|
|
|
|
mlaChunkedPrefill.cu
|
|
|
|
mlaChunkedPrefill.cuh
|
|
|
|
mlaKernels.cu
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
mlaKernels.h
|
|
|
|
moe_utils.cuh
|
|
|
|
moeAlignKernels.cu
|
|
|
|
moeAlignKernels.h
|
|
|
|
moeCommKernelsCommon.h
|
|
|
|
moePrepareKernels.cu
|
|
|
|
moePrepareKernels.h
|
|
|
|
moeTopKFuncs.cuh
|
|
|
|
multiHeadAttentionCommon.h
|
|
|
|
noAuxTcKernels.cu
|
[None][feat] Add routing support for the new model for both cutlass and trtllm moe backend (#9792)
|
2025-12-15 19:59:08 -08:00 |
|
noAuxTcKernels.h
|
|
|
|
penaltyKernels.cu
|
|
|
|
penaltyKernels.h
|
|
|
|
penaltyTypes.h
|
|
|
|
preQuantScaleKernel.cu
|
|
|
|
preQuantScaleKernel.h
|
|
|
|
qserveGemm.h
|
|
|
|
qserveGemmPerChannel.cu
|
|
|
|
qserveGemmPerGroup.cu
|
|
|
|
quantization.cu
|
[TRTLLM-9752][fix] WAR: Disable PDL for quant kernels to fix accuracy issues (#10285)
|
2026-01-03 14:34:55 +08:00 |
|
quantization.cuh
|
[TRTLLM-9578][feat] make PDL enabled by default (#9695)
|
2025-12-25 07:15:24 -05:00 |
|
quantization.h
|
|
|
|
recoverFromRingAtten.cu
|
|
|
|
recoverFromRingAtten.h
|
|
|
|
rmsnormKernels.cu
|
|
|
|
rmsnormKernels.h
|
|
|
|
sageAttentionKernels.cu
|
|
|
|
sageAttentionKernels.h
|
|
|
|
samplingAirTopPKernels.cu
|
|
|
|
samplingTopKKernels.cu
|
|
|
|
samplingTopKKernels.h
|
|
|
|
samplingTopPKernels.cu
|
|
|
|
samplingTopPKernels.h
|
|
|
|
sparseAttentionKernels.cu
|
|
|
|
sparseAttentionKernels.h
|
|
|
|
splitkGroupGemm.cu
|
|
|
|
splitkGroupGemm.h
|
|
|
|
stopCriteriaKernels.cu
|
|
|
|
stopCriteriaKernels.h
|
|
|
|
topkLastDim.cu
|
|
|
|
topkLastDim.h
|
|
|
|
unfusedAttentionKernels.cu
|
|
|
|
unfusedAttentionKernels.h
|
|
|
|
xqaDispatcher.cpp
|
[TRTLLM-9805][feat] Skip Softmax Attention. (#9821)
|
2025-12-21 02:52:42 -05:00 |
|
xqaDispatcher.h
|
|
|
