You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As for this topic, I'm wondering if SGLang supports the page attention kernel. In the Triton backend, it appears to be using flash attention. Is there any reason why SGLang chooses flash attention over page attention?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
As for this topic, I'm wondering if SGLang supports the page attention kernel. In the Triton backend, it appears to be using flash attention. Is there any reason why SGLang chooses flash attention over page attention?
Beta Was this translation helpful? Give feedback.
All reactions