latencypredictor: prediction server perf + mean + ensemble#2488
Merged
k8s-ci-robot merged 1 commit intoMar 10, 2026
Merged
Conversation
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
approved
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Comment on lines
-248
to
+259
| waiting = i % 10 + 1 | ||
| tokens = waiting | ||
| waiting = i % 10 # Include 0 to provide noqueue training data for ensemble | ||
| tokens = max(waiting, 1) |
Contributor
There was a problem hiding this comment.
What does the comment about including 0 here mean if we then cap the minimum at 1?
Contributor
Author
There was a problem hiding this comment.
oh previously waiting was >= 1, now we want to add 0 because that will trigger the no queue model
k8s-ci-robot
added
the
lgtm
Contributor
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: BenjaminBraunDev, kaushikmitr The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
BizerNotNull
pushed a commit
to BizerNotNull/gateway-api-inference-extension
that referenced
this pull request
Mar 15, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
predict_batch_fast()that extracts columns vianp.fromiterand buildspd.DataFrame(dict_of_arrays)instead ofpd.DataFrame(list_of_dicts), reducing/predict/bulk/strictlatency by ~41% (82ms → 48ms at 10k QPS)orjson+ORJSONResponsefor faster JSON serialization of bulk prediction responsesObjectiveType(mean/quantile) support to match training server changesQueueGatedModelensemble support — prediction server loads gated models, routes to noqueue/queued sub-models based onnum_request_waitingis_queuedbinary feature and_prepare_features_for_ensemble()to match training server feature engineering