perf: enable concurrent classification via Arc+clone #127
Conversation
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
Signed-off-by: cryo <[email protected]>
Signed-off-by: cryo <[email protected]>
✅ Deploy Preview for vllm-semantic-router ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
👥 vLLM Semantic Team NotificationThe following members have been identified for the changed files in this PR and have been automatically assigned: 📁
|
rootfs
reviewed
Sep 13, 2025
candle-binding/src/modernbert.rs
Outdated
| let classifier = classifier_arc.clone(); | ||
| drop(classifier_arc_opt); | ||
|
|
||
| match classifier.classify_text(text) { |
There was a problem hiding this comment.
Aha, let me try to fix it
Signed-off-by: cryo <[email protected]>
|
@cryo-zd thanks for making this happen! If you can have a followup PR for performance test suite to eval the latency with respect to concurrency, that'll be great! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
What type of PR is this?
perf: enable concurrent classification via Arc+clone
What this PR does / why we need it:
This PR updates the
MODERNBERT_CLASSIFIERdefinition to useArc<ModernBertClassifier>so that the global lock is only held for initialization. Subsequent calls now clone theArcand release the lock immediately, allowing concurrent inference without serialization.[concurrency-safe guarantee]
For now, only
MODERNBERT_CLASSIFIERis changed;MODERNBERT_PII_CLASSIFIERandMODERNBERT_JAILBREAK_CLASSIFIERremain unchanged, so that we can focus discussion on this design and trade-offs before extending it further.Which issue(s) this PR fixes:
Fixes #
Release Notes: Yes/No