Skip to content

Fix gRPC router workers never becoming ready with model set - #4270

Open
Bihan wants to merge 1 commit into
dstackai:masterfrom
Bihan:fix_issue_4240_router_group_health_probe
Open

Fix gRPC router workers never becoming ready with model set#4270
Bihan wants to merge 1 commit into
dstackai:masterfrom
Bihan:fix_issue_4240_router_group_health_probe

Conversation

@Bihan

@Bihan Bihan commented Sep 8, 2026

Copy link
Copy Markdown
Collaborator

This PR fixes #4240.

Setting model without probes derives a POST {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 /health and worker groups get no derived probe. Services without a router group keep the POST /v1/chat/completions probe.

@Bihan
Bihan requested review from r4victor and a lite review from Copilot and removed request for Copilot September 8, 2026 09:23
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.

[Bug]: gRPC router workers can never become ready when model is set

1 participant