Bump inference operator helm chart version to 2.2.2 with InitialRepli…#430
Open
ShreyaGangishetty wants to merge 1 commit into
Open
Conversation
…caCount deprecation
XuanCS
approved these changes
Jun 17, 2026
rgadagot
approved these changes
Jun 17, 2026
gongteng20001-cyber
approved these changes
Jun 17, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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's changing and why?
Bumping the
hyperpod-inference-operatorhelm chart from2.2.1to2.2.2to deprecate thespec.InitialReplicaCountfield on theInferenceEndpointConfigCRD.InitialReplicaCountwas dead code — defined in the CRD but never read by the controller, and functionally redundant withspec.Replicas(with thecurrentReplicasguard already in place). The field is kept in the schema for backward compatibility but flagged as deprecated.Customers should use:
spec.replicasfor initial pod countspec.autoScalingSpec.minReplicaCountfor the steady-state floor under autoscalingOperator
appVersionis unchanged at3.2(no binary changes — chart-only release).Before/After UX
Before:
kubectl explain inferenceendpointconfig.spec.InitialReplicaCountreturns the misleading "Number of desired pods" doc, suggesting customers should set it. The controller never reads it.After:
kubectl explainnow surfaces the deprecation notice with migration guidance.How was this change tested?
helm lint helm_chart/HyperPodHelmChart/charts/inference-operatorpasseshelm template helm_chart/HyperPodHelmChart/charts/inference-operatorpasses (rendering the deprecated field still works for backward compat)Are unit tests added?
No — chart-only metadata change; no application code modified.
Are integration tests added?
No — chart-only metadata change. The deprecation does not change runtime behavior.
Reviewer Guidelines
One of the following must be true: