fix(serve): Move endpoint reuse discovery to deploy time - #6142
Merged
mujtaba1747 merged 2 commits intoJul 31, 2026
Conversation
zhaoqizqwang
approved these changes
Jul 31, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Endpoint reuse depends on deploy-time context (instance_type is a
deploy() argument), so discovering and caching a candidate endpoint
during build() could produce a stale or mismatched match. Remove the
build-time endpoint lookup and the _reused_endpoint_name cache
re-validation, and let deploy() perform a single fresh discovery with
the requested instance type. build() now only handles Model reuse.
Also model_builder.build(reuse_resources) shouldn't be blocked on endpoint creation. That happens only at deploy() time.
Also add logging in the reuse status/polling helpers to surface
the current status of a matched resource and progress while waiting on
a Creating resource. Gives user visibility into the polling.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.