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
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
Uh oh!
There was an error while loading. Please reload this page.
-
我用vllm部署qwen3.5的时候用eager模式把cuda graph放到内存中,结果吞吐量会大幅下降,只有1/4到1/3。
但是qewn2.5就不会这样,虽然也会下降但很有限,至少还能保持9/10。
这是为啥呢?
Beta Was this translation helpful? Give feedback.
All reactions