ray serve inference improvements#2042
Open
zulissimeta wants to merge 6 commits into
Open
Conversation
zulissimeta
added
enhancement
zulissimeta
changed the title
zulissimeta
changed the title
lbluque
approved these changes
Jun 15, 2026
lbluque
left a comment
lbluque
left a comment
Contributor
There was a problem hiding this comment.
Thanks @zulissimeta! lg, just small comments.
| handle = serve.get_app_handle(deployment_name) | ||
| # ``_prefer_local_routing`` must be set via ``_init()`` before any | ||
| # ``.options()`` or ``.remote()`` call initializes the handle. | ||
| handle._init(_prefer_local_routing=True) |
Contributor
There was a problem hiding this comment.
can we set this using handle.options(_prefer_local_routing=True)?
| # users on slow CPUs can lengthen it). ``None`` disables the | ||
| # bound entirely so behavior matches the pre-timeout default | ||
| # if someone needs it. | ||
| self._request_timeout_s = _resolve_batch_server_timeout() |
Contributor
There was a problem hiding this comment.
Is it worth having this also be an explicit init kwarg with default to None which then searches for the env variable?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Three small changes to the ray serve deployment.
This PR
FAIRCHEM_BATCH_SERVER_TIMEOUT_S) to all of the .request() calls so that an indefinite hang (eg inference request when a server doesn't have enough resources to start inference service) eventually throws an error