Daniel Cámpora 1260e2f33f feat: Optimize TRTLLM Sampler perf single beam single step (#5550) ... Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>		2025-07-07 15:44:47 +02:00
..
batch_manager	refactor: decoding inputs (#5679)	2025-07-06 08:21:02 +02:00
common	Cherry pick "[NVBUG:5355009] Modify check for fuse_fp4_quant on SM120 (#5724)	2025-07-04 16:53:20 +09:00
cutlass_extensions/include/cutlass_extensions	opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222)	2025-06-26 12:18:19 +08:00
executor	feat: KV events for sliding window attention (#5580)	2025-07-05 06:05:20 +08:00
executor_worker	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
kernels	Refactor the topk parallelization part for the routing kernels (#5567)	2025-07-07 15:53:25 +08:00
layers	Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)	2025-05-12 22:32:29 +02:00
plugins	feat: reduce unnecessary kernel generation (#5476)	2025-07-04 14:37:49 +08:00
pybind	feat: Optimize TRTLLM Sampler perf single beam single step (#5550)	2025-07-07 15:44:47 +02:00
runtime	refactor: decoding inputs (#5679)	2025-07-06 08:21:02 +02:00
testing	fix: Improve chunking test and skip empty kernel calls (#5710)	2025-07-04 09:08:15 +02:00
thop	[TRTLLM-5812][feat] support FP8 row-wise dense GEMM in torch flow (#5615)	2025-07-07 18:04:57 +08:00
CMakeLists.txt	refactoring: port customized kernels with public cutlass version (#5027)	2025-06-13 16:19:31 +08:00