You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Reuses one direct reranking provider and REST client per provider/model.
Removes synchronized per-request client construction and closes cached clients at shutdown.
Makes the shared HTTP/1 connection pool explicit and configurable per model; the default remains 50.
Keeps gateway providers request-scoped and preserves per-call bearer tokens and tenant headers.
Bounds client and connection growth; it does not claim increased NIM capacity.
Validation: 34 focused reranking and findAndRerank tests pass. End-to-end throughput still requires an A/B deployment because the direct NIM harness bypasses this client.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this PR does:
Validation: 34 focused reranking and findAndRerank tests pass. End-to-end throughput still requires an A/B deployment because the direct NIM harness bypasses this client.
Which issue(s) this PR fixes:
Fixes #2573
Checklist