kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
cbc67b7c76
TensorRT-LLMs/cpp/tensorrt_llm/kernels/cutlass_kernels
History
Min Yu 9cae7277ea
[https://nvbugs/5726962][feat] Apply fusion for W4AFP8_AWQ MoE (#9838) 
Signed-off-by: Min Yu <171526537+yumin066@users.noreply.github.com>
Signed-off-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
Co-authored-by: Anthony Chang <27950904+rosenrodt@users.noreply.github.com>
2026-01-06 10:16:41 +08:00
..
allreduce_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fp4_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fp8_blockscale_gemm [None][feat] Drop non-deepgemm fp8 block scale gemm (#10256) 2025-12-25 14:52:52 +08:00
fp8_rowwise_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
fpA_intB_gemm [None][feat] sm100 weight-only kernel (#10190) 2026-01-05 09:44:36 +08:00
fused_gated_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
include [https://nvbugs/5726962][feat] Apply fusion for W4AFP8_AWQ MoE (#9838) 2026-01-06 10:16:41 +08:00
int8_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
low_latency_gemm [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
moe_gemm [https://nvbugs/5726962][feat] Apply fusion for W4AFP8_AWQ MoE (#9838) 2026-01-06 10:16:41 +08:00
python [https://nvbugs/5726962][feat] Apply fusion for W4AFP8_AWQ MoE (#9838) 2026-01-06 10:16:41 +08:00
CMakeLists.txt [https://nvbugs/5690172][fix] Fix Qwen3-235B ATP accuracy issue with PDL (#9530) 2025-12-01 09:10:21 +08:00
cutlass_heuristic.cpp [None][feat] sm100 weight-only kernel (#10190) 2026-01-05 09:44:36 +08:00
cutlass_heuristic.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cutlass_preprocessors.cpp [None][feat] sm100 weight-only kernel (#10190) 2026-01-05 09:44:36 +08:00
cutlass_preprocessors.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cutlass_type_conversion.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00