Slo prediction experimental #1677
Merged
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
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
the
size/XXL
|
/lgtm |
k8s-ci-robot
added
the
lgtm
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: kaushikmitr, kfswain The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
k8s-ci-robot
added
the
approved
k8s-ci-robot
merged commit 0901896
into
kubernetes-sigs:slo-prediction-experimental
8 checks passed
kaushikmitr
added a commit
to tomatillo-and-multiverse/gateway-api-inference-extension-slo
that referenced
this pull request
Oct 7, 2025
* add latency predictor build readme * update test dual server * allow batch prediction * allow batch prediction, update slo headers to all small
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
PR #1677 – Add batch prediction capability and lightGBM support to prediction sidecars
Overview
This PR enhances the latency predictor and scheduling pipeline in the Gateway API Inference Extension, introducing batch prediction support, consistent SLO header handling, improved test/deployment flows, and infrastructure updates. Batch predictions (prediction TTFT/TPOT for all pods in a single API call to the sidecars) makes things much more efficient.
Key Changes
Batch Prediction & SLO Headers
latencypredictor_async.go) and updated tests.Prediction Server & Model Support
libgomp1) to prevent OpenMP errors.prediction_server.pylogic to support multiple models and fallback handling.Testing & CI/CD
Dockerfile-testthat builds a containerized test image runningpytestby default.build-deploy.shwith new commands (test,test-deploy,all,images) to automate build → deploy → test workflows.test-dual-server-deployment.yaml) for end-to-end CI-like test execution.