3 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Jue Wang	5972f97f11	Remove naive rotary forward overriding. (#19263)	2026-03-03 21:50:40 -08:00
Jue WANG	138ff23187	Allow to disable batch decoding. (#11944)	2025-10-22 21:57:12 -07:00
Jue WANG	9c53dad809	Fix MTP MoE weight loading with NVFP4 target model. (#10758)	2025-09-22 14:21:57 -07:00