Arctic rollout: override Ray's default max_concurrency (1000 -> 4096) - #9
Merged
sfc-gh-mhidayetoglu merged 1 commit intoJun 30, 2026
Conversation
| server = self.server_class.options().remote( | ||
| server = self.server_class.options( | ||
| # override ray's default max_concurrency of 1000 | ||
| max_concurrency=4096, |
Collaborator
There was a problem hiding this comment.
Hard coding in this manner does not generalize. It would be better to make this an arctic config knob since it is arctic-specific.
Author
There was a problem hiding this comment.
we can make it max_concurrency = #replicas x vllm.max_num_seqs
Collaborator
There was a problem hiding this comment.
Yes, that would be excellent. Thanks.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Override ray's default max_concurrency of 1000 -> 4096 so that each engine is filled with requests at scale.