-
Notifications
You must be signed in to change notification settings - Fork 69
In hermetic test, add additional test cases and move k8sClient object creation so it's called once for all tests #278
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
In hermetic test, add additional test cases and move k8sClient object creation so it's called once for all tests #278
Conversation
… setup to BeforeSuit() so it is set up once for all test cases. Add getter function to scheduling to reference queue threshold for lora affinity inside integration tests.
Hi @BenjaminBraunDev. Thanks for your PR. I'm waiting for a kubernetes-sigs member to verify that this patch is reasonable to test. If it is, they should reply with Once the patch is verified, the new status will be reflected by the I understand the commands that are listed here. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. |
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
…ts, remove unreachable error check.
/ok-to-test |
/approve leaving lgtm to @liu-cong |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ahg-g, BenjaminBraunDev 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 |
… non-lora test case to use a different model name.
/lgtm |
Adds additional testing for EPP logic for selecting model servers for an inference request. The two new test cases check:
queueingThresholdLoRA
than a lower queue size model is chosen despite the higher already having the requested LoRA active to avoid overloading a heavy traffic model.This also moves the logic for adding test
InferenceModel
andInferencePool
objects into the k8sClient into theBeforeSuit()
so it's only called once, otherwise it will error upon trying to create duplicate objects.Related Issue: #80