Yukun He 9cc5922a0b Clean up allreduce op in Deepseek V3 model. (#3829) ... * Replace deepseek_allreduce op with the new unified allreduce op and moe_allreduce op. * Minor revision of moe_allreduce op argument names. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-05-01 07:56:36 +08:00
..
batch_manager	cacheTransceiver buffer manager (#3798)	2025-04-27 11:48:15 +08:00
common	fix: [https://nvbugspro.nvidia.com/bug/5243482] If FlashMLA is used, the existence of FMHA based MLA kernels should not be checked. (#3862)	2025-04-30 14:27:38 +08:00
cutlass_extensions/include/cutlass_extensions	TRTLLM-4624 feat: Add nvfp4 gemm and moe support for SM120 (#3770)	2025-04-29 11:19:11 -04:00
executor	cacheTransceiver buffer manager (#3798)	2025-04-27 11:48:15 +08:00
executor_worker	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
kernels	chore: update internal_cutlass_kernels. (#3973)	2025-04-30 22:13:17 +08:00
layers	fix: Eagle decoding (#3456)	2025-04-11 22:06:38 +08:00
plugins	TRTLLM-4624 feat: Add nvfp4 gemm and moe support for SM120 (#3770)	2025-04-29 11:19:11 -04:00
pybind	cacheTransceiver buffer manager (#3798)	2025-04-27 11:48:15 +08:00
runtime	fix: 5197419 and removed unused runtime kernels (#3631)	2025-04-23 18:04:50 +02:00
thop	Clean up allreduce op in Deepseek V3 model. (#3829)	2025-05-01 07:56:36 +08:00
CMakeLists.txt	infra: open source XQA kernels (#3762)	2025-04-30 18:05:15 +08:00