Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
Yongye Zhu
parent
3ce15fd574
commit
44d95069e9
@@ -86,6 +86,10 @@ class DeepseekV4FlashMLABackend(AttentionBackend):
|
||||
def is_sparse(cls) -> bool:
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def supports_sink(cls) -> bool:
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def supports_compute_capability(cls, capability: DeviceCapability) -> bool:
|
||||
return capability.major in [9, 10]
|
||||
|
||||
Reference in New Issue
Block a user