| .. |
|
allreduce_gemm
|
fix TMA error with GEMM+AR on TP=2 (#6075)
|
2025-07-18 10:26:08 +08:00 |
|
fp4_gemm
|
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568)
|
2025-09-16 09:56:18 +08:00 |
|
fp8_blockscale_gemm
|
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568)
|
2025-09-16 09:56:18 +08:00 |
|
fp8_rowwise_gemm
|
feat: reduce unnecessary kernel generation (#5476)
|
2025-07-04 14:37:49 +08:00 |
|
fpA_intB_gemm
|
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568)
|
2025-09-16 09:56:18 +08:00 |
|
fused_gated_gemm
|
feat: reduce unnecessary kernel generation (#5476)
|
2025-07-04 14:37:49 +08:00 |
|
include
|
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568)
|
2025-09-16 09:56:18 +08:00 |
|
int8_gemm
|
[None][perf] Make finalize fusion part of the tactic selection logic (#6915)
|
2025-08-21 14:08:03 -07:00 |
|
low_latency_gemm
|
feat: reduce unnecessary kernel generation (#5476)
|
2025-07-04 14:37:49 +08:00 |
|
moe_gemm
|
[TRTLLM-6286] [perf] Add NoSmem epilogue schedule and dynamic cluster shape for sm10x group gemm (#7757)
|
2025-09-21 11:38:17 +08:00 |
|
python
|
[TRTLLM-6286] [feat] Update CUTLASS to 4.2 and enable SM103 group gemm (#7832)
|
2025-09-19 09:50:54 +08:00 |
|
CMakeLists.txt
|
[TRTLLM-6286] [perf] Add NoSmem epilogue schedule and dynamic cluster shape for sm10x group gemm (#7757)
|
2025-09-21 11:38:17 +08:00 |
|
cutlass_heuristic.cpp
|
[TRTLLM-6286] [perf] Add NoSmem epilogue schedule and dynamic cluster shape for sm10x group gemm (#7757)
|
2025-09-21 11:38:17 +08:00 |
|
cutlass_heuristic.h
|
[None][perf] Add MOE support for dynamic cluster shapes and custom epilogue schedules (#6126)
|
2025-09-02 21:54:43 -04:00 |
|
cutlass_preprocessors.cpp
|
[TRTLLM-5366][feat]Add support for sm121 (#5524)
|
2025-07-08 14:27:00 -07:00 |
|
cutlass_preprocessors.h
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
cutlass_type_conversion.h
|
chore: cutlass cleanup (#3165)
|
2025-04-01 13:57:38 +08:00 |
822cb0115b