Fix gRPC router workers never becoming ready with model set - #4270
Open
Bihan wants to merge 1 commit into
Open
Conversation
Bihan
requested review from
r4victor
and
a lite review from Copilot
and removed request for
Copilot
September 8, 2026 09:23
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes #4240.
Setting
modelwithoutprobesderives aPOST {prefix}/chat/completionsprobe. ` A gRPC worker cannot answer HTTP at all, and the router answers 404 until workers are registered with it — but registration only considers ready jobs, so readiness waits on registration and vice versa.Implements the third option from the issue: #4240
The third option tells:
At minimum, do not apply the model default probe to non-router replica groups, and log when the router-worker sync returns early because no ready router job was found.With this fix, in a service with a router group, the router is probed with
GET /healthand worker groups get no derived probe. Services without a router group keep thePOST /v1/chat/completionsprobe.