..
allgatherOp.cpp
[fix] Move NCCL group in all-gather and reduce-scatter OPs outside the outer loop ( #6053 )
2025-07-16 00:25:32 +09:00
allreduceOp.cpp
perf: better heuristic for allreduce ( #5432 )
2025-07-01 22:56:06 -04:00
attentionOp.cpp
[ https://nvbugs/5387771 ] fix deadlocks due to insufficient numSemaphores ( #6262 )
2025-07-23 11:20:55 +08:00
causalConv1dOp.cpp
fix: fix license bug ( #5200 )
2025-06-13 18:58:15 +08:00
CMakeLists.txt
[TRTLLM-5863][feat] Support Weight-Only-Quantization in PyTorch Workflow ( #5850 )
2025-07-21 15:17:35 +08:00
convertSpecDecodingMaskToPackedMaskOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
cublasScaledMM.cpp
[TRTLLM-4279] fix: Add a protection test for checking trtllm custom ops ( #6515 )
2025-08-01 15:59:09 +08:00
cublasScaledMM.h
Feat/ds r1 min latency opt round3, add router gemm, fused a gemm, PDL ( #4560 )
2025-06-14 17:36:22 +08:00
cudaScaledMM.cpp
[NVBUG-5304516/5319741]Qwen2.5VL FP8 support ( #5029 )
2025-07-09 23:16:42 +08:00
cutlassScaledMM.cpp
refactoring: port customized kernels with public cutlass version ( #5027 )
2025-06-13 16:19:31 +08:00
dsv3FusedAGemmOp.cpp
Feat/ds r1 min latency opt round3, add router gemm, fused a gemm, PDL ( #4560 )
2025-06-14 17:36:22 +08:00
dsv3RouterGemmOp.cpp
Feat/ds r1 min latency opt round3, add router gemm, fused a gemm, PDL ( #4560 )
2025-06-14 17:36:22 +08:00
dynamicDecodeOp.cpp
Feat: Variable-Beam-Width-Search (VBWS) part3 ( #3338 )
2025-04-08 23:51:27 +08:00
dynamicDecodeOp.h
Update TensorRT-LLM ( #2783 )
2025-02-13 18:40:22 +08:00
finegrained_mixed_dtype_gemm_thop.cpp
W4A8 GEMM ( #6005 )
2025-07-20 17:34:57 +03:00
finegrained_mixed_dtype_gemm_thop.h
W4A8 GEMM ( #6005 )
2025-07-20 17:34:57 +03:00
fmhaPackMaskOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
fp4BatchedQuantize.cpp
update FP4 quantize layout ( #3045 )
2025-04-03 13:13:54 -04:00
fp4BlockScaleMoe.cpp
[nvbugs/5336321][fix] Enable attention dp = False test case, Fix TRTLLM Gen Moe workspace allocation ( #5463 )
2025-07-14 17:17:30 +08:00
fp4Gemm.cpp
feat: Add w4a8_mxfp4_fp8 quantization recipe. ( #4867 )
2025-06-16 11:30:57 +08:00
fp4GemmTrtllmGen.cpp
feat: update DeepSeek FP8 TRT-LLM Gen cubins ( #4643 )
2025-06-03 14:07:54 -07:00
fp4Op.cpp
[feat] Support torch compile for attention dp ( #5086 )
2025-07-01 13:48:52 -04:00
fp4Quantize.cpp
feat: Fallback to NCCL for various patterns when input size is large. ( #4080 )
2025-05-08 11:13:13 -07:00
fp4Quantize.h
feat: Fallback to NCCL for various patterns when input size is large. ( #4080 )
2025-05-08 11:13:13 -07:00
fp8BatchedGemmTrtllmGen.cpp
[TRTLLM-5589] feat: Minor optimizations for tunable FP8 batched GEMM op. ( #5139 )
2025-06-18 14:33:46 +08:00
fp8BlockScaleMoe.cpp
[TRTLLM-6100] fix: Nvbug 5356427: autotuned TRTLLM Gen fp8 block scale MoE illegal memory access ( #5676 )
2025-07-14 17:17:30 +08:00
fp8BlockScalingGemm.cpp
feat: update DeepSeek FP8 TRT-LLM Gen cubins ( #4643 )
2025-06-03 14:07:54 -07:00
fp8Op.cpp
feat: Fallback to NCCL for various patterns when input size is large. ( #4080 )
2025-05-08 11:13:13 -07:00
fp8Op.h
feat: Fallback to NCCL for various patterns when input size is large. ( #4080 )
2025-05-08 11:13:13 -07:00
fp8PerTensorScaleMoe.cpp
[TRTLLM-5770] feat: Integrate TRT-LLM Gen FP8 block scale MoE with Pytorch workflow kernel autotuner ( #5207 )
2025-06-17 21:01:56 +08:00
fp8PerTensorScalingTrtllmGenGemm.cpp
feat: update DeepSeek FP8 TRT-LLM Gen cubins ( #4643 )
2025-06-03 14:07:54 -07:00
fp8Quantize.cpp
[feat] open source fp8_blockscale_gemm ( #3071 )
2025-04-02 12:12:52 +08:00
fp8RowwiseGemm.cpp
[TRTLLM-5812][feat] support FP8 row-wise dense GEMM in torch flow ( #5615 )
2025-07-07 18:04:57 +08:00
fusedQKNormRopeOp.cpp
[ https://nvbugs/5340941 ] - fix: Correct custom ops used by Qwen3 Moe … ( #6285 )
2025-07-25 14:49:45 +08:00
fusedTopkSoftmax.cpp
refactoring: port customized kernels with public cutlass version ( #5027 )
2025-06-13 16:19:31 +08:00
gatherTreeOp.cpp
[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow ( #4092 )
2025-05-14 23:10:04 +02:00
groupRmsNormOp.cpp
feat: Add heuristic for GroupRMSNorm kernel selection. ( #4047 )
2025-05-13 08:52:53 +08:00
llama4MinLatency.cpp
Cherry pick feat/llama4 to main ( #4739 )
2025-05-30 05:28:40 +08:00
logitsBitmaskOp.cpp
[TRTLLM-6406] feat: Enable guided decoding with overlap scheduler ( #6000 )
2025-07-17 17:46:10 +08:00
loraOp.cpp
added loraOp into lora layer + test for mlp and comparison to lora plugin ( #3455 )
2025-04-17 12:48:27 +08:00
mambaConv1dOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
mlaPreprocessOp.cpp
[TRTLLM-3602][feat] support nvfp4 model and fp8 kv cache for MLA chunked prefill (Blackwell) ( #5475 )
2025-06-26 22:18:08 +08:00
moeCommOp.cpp
[NvBug 5378370] fix: Fix alltoall for llama4 (apply_router_weight_on_input=True) ( #5902 )
2025-07-12 15:50:31 +09:00
moeLoadBalanceOp.cpp
feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) ( #5226 )
2025-06-25 22:25:13 -07:00
moeOp.cpp
[fix] Fix MoE workspace info by storing Torch tensor itself instead of data_ptr ( #5900 )
2025-07-10 20:07:32 +09:00
moeUtilOp.cpp
feat: Add support for MXFP8xMXFP4 in pytorch ( #5535 )
2025-07-06 15:32:06 -07:00
mtpOp.cpp
fix: refactor and fix mtp vanilla ( #4762 )
2025-06-20 05:23:39 +08:00
ncclCommunicatorOp.cpp
feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism ( #4034 )
2025-05-16 04:16:53 +08:00
ncclCommunicatorOp.h
feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism ( #4034 )
2025-05-16 04:16:53 +08:00
noAuxTcOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
parallelDecodeKVCacheUpdateOp.cpp
Update TensorRT-LLM ( #2582 )
2024-12-16 21:50:47 -08:00
redrafterCurandOp.cpp
[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow ( #4092 )
2025-05-14 23:10:04 +02:00
reducescatterOp.cpp
[fix] Move NCCL group in all-gather and reduce-scatter OPs outside the outer loop ( #6053 )
2025-07-16 00:25:32 +09:00
relativeAttentionBiasOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
renormMoeRoutingOp.cpp
[ https://nvbugs/5340941 ] - fix: Correct custom ops used by Qwen3 Moe … ( #6285 )
2025-07-25 14:49:45 +08:00
selectiveScanOp.cpp
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
thUtils.cpp
Update TensorRT-LLM ( #2849 )
2025-03-04 18:44:00 +08:00
thUtils.h
[TRTLLM-5812][feat] support FP8 row-wise dense GEMM in torch flow ( #5615 )
2025-07-07 18:04:57 +08:00
userbuffersFinalizeOp.cpp
feat: Introduce UB allocator for pytorch flow ( #3257 )
2025-04-08 18:39:49 +08:00
userbuffersTensor.cpp
feat: Introduce UB allocator for pytorch flow ( #3257 )
2025-04-08 18:39:49 +08:00
userbuffersTensor.h
feat: Introduce UB allocator for pytorch flow ( #3257 )
2025-04-08 18:39:49 +08:00
weightOnlyQuantGemm.cpp
[TRTLLM-5863][feat] Support Weight-Only-Quantization in PyTorch Workflow ( #5850 )
2025-07-21 15:17:35 +08:00
weightOnlyQuantGemm.h
[TRTLLM-5863][feat] Support Weight-Only-Quantization in PyTorch Workflow ( #5850 )
2025-07-21 15:17:35 +08:00
weightOnlyQuantOp.cpp
chore: remove usernames from comments ( #3291 )
2025-04-05 13:44:28 +08:00
ac23f4a80d