| .. |
|
beamSearchKernels
|
|
|
|
causalConv1d
|
|
|
|
communicationKernels
|
[TRTLLM-7318][feat] MnnvlThroughput AlltoAll implementation. (#7499)
|
2025-10-27 13:23:06 -04:00 |
|
contextFusedMultiHeadAttention
|
[https://nvbugs/5542862][fix] Upgrade fmha_v2. (#8364)
|
2025-10-20 10:20:23 +08:00 |
|
cutlass_kernels
|
[None][feat] Add FP8 rowwise GEMMs for B200 (#8332)
|
2025-10-27 16:33:14 -04:00 |
|
decoderMaskedMultiheadAttention
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
dsv3MinLatencyKernels
|
|
|
|
flashMLA
|
|
|
|
fusedLayernormKernels
|
|
|
|
groupRmsNormKernels
|
|
|
|
internal_cutlass_kernels
|
[None][fix] Fix the performance issue of FP8 blockwise grouped GEMM when using attention DP (#8501)
|
2025-10-27 10:18:19 +08:00 |
|
llama4MinLatencyKernels
|
|
|
|
lora
|
|
|
|
moeLoadBalance
|
[None][fix] fix EPLB init hang (#8649)
|
2025-10-28 05:22:49 -04:00 |
|
selectiveScan
|
|
|
|
speculativeDecoding
|
|
|
|
tinygemm2
|
[TRTLLM-7775][feat] Integrate tinygemm2 for gpt-oss (#7916)
|
2025-10-02 10:47:04 -07:00 |
|
trtllmGenKernels
|
[None][feat] Update TRTLLM MoE MxFP4 cubins; autotune tileN (#8156)
|
2025-10-23 09:14:18 +08:00 |
|
unfusedAttentionKernels
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
userbuffers
|
|
|
|
weightOnlyBatchedGemv
|
|
|
|
attentionMask.cu
|
|
|
|
attentionMask.h
|
|
|
|
banBadWords.cu
|
|
|
|
banBadWords.h
|
|
|
|
banRepeatNgram.cu
|
|
|
|
banRepeatNgram.h
|
|
|
|
beamSearchKernels.cu
|
|
|
|
beamSearchKernels.h
|
|
|
|
buildRelativeAttentionBiasKernel.cu
|
|
|
|
buildRelativeAttentionBiasKernel.h
|
|
|
|
CMakeLists.txt
|
|
|
|
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
|
[None][feat] Add fmha_v2 kernel for head_dim=80 and sm=100 to support VLM (#8392)
|
2025-10-17 19:42:47 +08:00 |
|
fmhaDispatcher.h
|
|
|
|
fusedMoeCommKernels.cu
|
[TRTLLM-6748][feat] add PDL support for more kernels (#7977)
|
2025-10-11 08:32:05 +08:00 |
|
fusedMoeCommKernels.h
|
[TRTLLM-6748][feat] add PDL support for more kernels (#7977)
|
2025-10-11 08:32:05 +08:00 |
|
fusedQKNormRopeKernel.cu
|
[None][feat] Support Qwen3 next (#7892)
|
2025-09-29 21:16:07 +08:00 |
|
fusedQKNormRopeKernel.h
|
|
|
|
gptKernels.cu
|
|
|
|
gptKernels.h
|
|
|
|
groupGemm.cu
|
|
|
|
groupGemm.h
|
|
|
|
kvCachePartialCopy.cu
|
|
|
|
kvCacheUtils.h
|
|
|
|
layernormKernels.cu
|
|
|
|
layernormKernels.h
|
|
|
|
logitsBitmask.cu
|
|
|
|
logitsBitmask.h
|
|
|
|
lookupKernels.cu
|
|
|
|
lookupKernels.h
|
|
|
|
lruKernel.cu
|
|
|
|
lruKernel.h
|
|
|
|
mambaConv1dKernels.cu
|
|
|
|
mambaConv1dKernels.h
|
|
|
|
mlaChunkedPrefill.cu
|
|
|
|
mlaChunkedPrefill.cuh
|
|
|
|
mlaKernels.cu
|
|
|
|
mlaKernels.h
|
|
|
|
moe_utils.cuh
|
[https://nvbugs/5378031] [feat] W4A8 AWQ MoE supports Per Expert Pre-quant Scale Factor for PyT backend (#7286)
|
2025-10-16 11:07:48 +08:00 |
|
moeCommKernelsCommon.h
|
|
|
|
moePrepareKernels.cu
|
[TRTLLM-6748][feat] add PDL support for more kernels (#7977)
|
2025-10-11 08:32:05 +08:00 |
|
moePrepareKernels.h
|
[TRTLLM-6748][feat] add PDL support for more kernels (#7977)
|
2025-10-11 08:32:05 +08:00 |
|
moeTopKFuncs.cuh
|
[TRTLLM-8637][feat] Optimize the routing kernel for DeepseekV3 (MoE CUTLASS backend); Add support for KimiK2 and Qwen-next (MoE TRTLLM backend) (#7761)
|
2025-10-20 10:08:31 +08:00 |
|
multiHeadAttentionCommon.h
|
|
|
|
noAuxTcKernels.cu
|
[TRTLLM-8637][feat] Optimize the routing kernel for DeepseekV3 (MoE CUTLASS backend); Add support for KimiK2 and Qwen-next (MoE TRTLLM backend) (#7761)
|
2025-10-20 10:08:31 +08:00 |
|
noAuxTcKernels.h
|
[TRTLLM-8637][feat] Optimize the routing kernel for DeepseekV3 (MoE CUTLASS backend); Add support for KimiK2 and Qwen-next (MoE TRTLLM backend) (#7761)
|
2025-10-20 10:08:31 +08:00 |
|
penaltyKernels.cu
|
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)
|
2025-10-27 13:12:31 -04:00 |
|
penaltyKernels.h
|
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)
|
2025-10-27 13:12:31 -04:00 |
|
penaltyTypes.h
|
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)
|
2025-10-27 13:12:31 -04:00 |
|
preQuantScaleKernel.cu
|
[https://nvbugs/5378031] [feat] W4A8 AWQ MoE supports Per Expert Pre-quant Scale Factor for PyT backend (#7286)
|
2025-10-16 11:07:48 +08:00 |
|
preQuantScaleKernel.h
|
[https://nvbugs/5378031] [feat] W4A8 AWQ MoE supports Per Expert Pre-quant Scale Factor for PyT backend (#7286)
|
2025-10-16 11:07:48 +08:00 |
|
qserveGemm.h
|
|
|
|
qserveGemmPerChannel.cu
|
|
|
|
qserveGemmPerGroup.cu
|
|
|
|
quantization.cu
|
|
|
|
quantization.cuh
|
|
|
|
quantization.h
|
|
|
|
recoverFromRingAtten.cu
|
[https://nvbugs/5503138] [fix] Remove compile warnings (#8167)
|
2025-10-13 13:24:23 +08:00 |
|
recoverFromRingAtten.h
|
|
|
|
rmsnormKernels.cu
|
|
|
|
rmsnormKernels.h
|
|
|
|
sageAttentionKernels.cu
|
|
|
|
sageAttentionKernels.h
|
|
|
|
samplingAirTopPKernels.cu
|
|
|
|
samplingTopKKernels.cu
|
|
|
|
samplingTopKKernels.h
|
|
|
|
samplingTopPKernels.cu
|
|
|
|
samplingTopPKernels.h
|
|
|
|
sparseAttentionKernels.cu
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
sparseAttentionKernels.h
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
splitkGroupGemm.cu
|
|
|
|
splitkGroupGemm.h
|
|
|
|
stopCriteriaKernels.cu
|
|
|
|
stopCriteriaKernels.h
|
|
|
|
topkLastDim.cu
|
|
|
|
topkLastDim.h
|
|
|
|
unfusedAttentionKernels.cu
|
|
|
|
unfusedAttentionKernels.h
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
xqaDispatcher.cpp
|
[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)
|
2025-10-14 08:23:16 -07:00 |
|
xqaDispatcher.h
|
|
|
