Skip to content

Conversation

finbarrtimbers
Copy link
Collaborator

@finbarrtimbers finbarrtimbers commented Sep 3, 2025

As part of #859, I made a number of major changes. To be a better software engineer, I'm breaking them out into separate PRs (and also because there's a bug in #859 that I can't identify).

Previously, process_from_queue would only process a single request and then return. Now, it keeps processing requests until should_stop is set.

Runs:

Single GPU: Beaker
Multi-node: Beaker
Single GPU with tool use: Beaker

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.

1 participant