How to batch generating the tokens? #631
Unanswered
zhanghaohit
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I saw the
generate_longmethod is generating tokens one by one. It is quite slow (CPU device), around 0.2 second per token. For a number of 30 tokens for just "hello world", it takes > 6 seconds.Is there a way to batch the generating process?
Beta Was this translation helpful? Give feedback.
All reactions