3 Commits

Author	SHA1	Message	Date
Rain Jiang	79e6a8a6ac	support cuda 13.0 and trtllm kernel by Aug 25 2025 (#9495)	2025-08-26 23:13:27 -07:00
Yi Zhang	2998c4bdf4	[optimize] fuse renormalize into moe_topk_softmax (#7744) ... Co-authored-by: ispobock <ispobaoke@gmail.com>	2025-07-03 12:42:44 -07:00
Qingquan Song	61e4433caf	Add moe topk softmax templated from vllm (#4302)	2025-03-14 12:03:33 -07:00