Skip to content

Conversation

@rainyfly
Copy link
Collaborator

When a request is preempted and recovered again, we should prefill all the tokens (including prompt tokens and output tokens).

@paddle-bot
Copy link

paddle-bot bot commented Jul 29, 2025

Thanks for your contribution!

@rainyfly rainyfly closed this Jul 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants