4 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Qingquan Song	044c315970	Make torch compile configurable for biased_grouped_topk (#4749)	2025-03-28 10:57:52 -07:00
Qingquan Song	6ffb6bd47a	Fix fa3 cuda graph page_size > 1 precision and page_size=1 speed (#4855)	2025-03-28 01:35:59 -07:00
Qingquan Song	61e4433caf	Add moe topk softmax templated from vllm (#4302)	2025-03-14 12:03:33 -07:00
Qingquan Song	4068e01292	Fix per token fp8 quant precision (#4362)	2025-03-12 21:19:05 -07:00