Xiaowei Wang 32dfdfba30 feat: fuse w4a8 moe pre-quant scale on Hopper (#5613) ... Signed-off-by: Xiaowei Wang <100599594+xiaoweiw-nv@users.noreply.github.com>		2025-07-01 23:02:41 -04:00
..
batch_manager	refactor: decoder state setup (#5093)	2025-06-30 11:09:43 +02:00
common	feat: chunked prefill for MLA (Blackwell) (#4651)	2025-06-26 09:01:00 +08:00
cutlass_extensions/include/cutlass_extensions	opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222)	2025-06-26 12:18:19 +08:00
executor	[TRTLLM-5000][feat] NGrams V2 (#4569)	2025-06-27 23:00:17 +08:00
executor_worker	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
kernels	feat: fuse w4a8 moe pre-quant scale on Hopper (#5613)	2025-07-01 23:02:41 -04:00
layers	Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)	2025-05-12 22:32:29 +02:00
plugins	opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222)	2025-06-26 12:18:19 +08:00
pybind	refactor: decoder state setup (#5093)	2025-06-30 11:09:43 +02:00
runtime	refactor: Clean up DecodingInput and DecodingOutput (#5617)	2025-07-01 14:31:42 +02:00
testing	refactor: Move ModelSpec to core library (#3980)	2025-05-04 01:39:09 +08:00
thop	perf: better heuristic for allreduce (#5432)	2025-07-01 22:56:06 -04:00
CMakeLists.txt	refactoring: port customized kernels with public cutlass version (#5027)	2025-06-13 16:19:31 +08:00