[Model] add GLM-5.3-Flash support (#53906)

This commit is contained in:
Jiangyun Zhu
2026-09-03 09:40:35 -07:00
committed by GitHub
parent da8ec28268
commit 98ed0856f3
94 changed files with 17927 additions and 266 deletions
@@ -1534,7 +1534,7 @@ class MLACommonBackend(AttentionBackend):
@classmethod
def get_supported_head_sizes(cls) -> list[int]:
return [320, 576]
return [320, 512, 576]
@classmethod
def is_mla(cls) -> bool: