[Model] add GLM-5.3-Flash support (#53906)
This commit is contained in:
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user