test: added latency predictor converage for inferencepool and added convera…#2187
Conversation
…ge for epp standalone mode
|
@capri-xiyue: The label(s) DetailsIn response to this:
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 project configuration. |
|
/assign @zetxqx |
|
assign @ahg-g |
| # Training Server Configuration | ||
| trainingServer: | ||
| image: | ||
| hub: path/to/your/docker/repo # NOTE: Update with your Docker repository path for sidecars |
| @@ -1,5 +1,5 @@ | |||
| {{- define "inference-extension.gke" -}} | |||
| {{- if eq (lower .Values.provider.name) "gke" }} | |||
| {{- if and .Values.provider (eq (lower .Values.provider.name) "gke") }} | |||
There was a problem hiding this comment.
Previously in inferencepool helm chart, as the values.yaml provides a none as a default, we won't have issues. But in epp-standalone helm chart, the default "none" was not provided. Therefore, it will encounter issue. I've made default "none" in this PR and here check provider exists before before accessing the value(more defensive). I was testing "gke" set up, therefore didn't notice this when there was no provider value.
|
why do we have a test as a prefix to the PR title? |
|
I am not aware of that convention :) But also, isn't the primary purpose of this PR is adding the latency predictor to the standalone? |
My primary purpose is to add helm template coverage to both inferencepool helm chart and epp standalone chart. |
|
/lgtm |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ahg-g, capri-xiyue 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 |
…ge for epp standalone mode
What type of PR is this?
/kind test
What this PR does / why we need it:
Added test coverage for inferencepool with latency predictor and test converage for epp standalone mode
Which issue(s) this PR fixes:
Fixes #2173
Does this PR introduce a user-facing change?: