Make apiVersion configurable for inferencePool in the helm charts

[rahulgurnani]

What type of PR is this?

/kind bug

What this PR does / why we need it:

Which issue(s) this PR fixes:

Fixes #1541

Does this PR introduce a user-facing change?:

cc @nirrozenbaum

[netlify]

✅ Deploy Preview for gateway-api-inference-extension ready!

Name	Link
🔨 Latest commit	4ebab20
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/68bcaca4cd854e00083d3524
😎 Deploy Preview	https://deploy-preview-1542--gateway-api-inference-extension.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[k8s-ci-robot]

Hi @rahulgurnani. 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 /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work. Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

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.

[rahulgurnani]

Tested:

rahulgurnani@rahulgurnani3:~/gateway-api-inference-extension/config/charts/inferencepool$ helm template .  --debug --set  inferencePool.apiVersion=inference.networking.k8s.io/v1alpha1
install.go:225: 2025-09-05 19:45:49.147211813 +0000 UTC m=+0.062051816 [debug] Original chart version: ""
install.go:242: 2025-09-05 19:45:49.147334015 +0000 UTC m=+0.062173996 [debug] CHART PATH: /usr/local/google/home/rahulgurnani/gateway-api-inference-extension/config/charts/inferencepool

---
...
---
# Source: inferencepool/templates/inferencepool.yaml
apiVersion: inference.networking.k8s.io/v1alpha1
kind: InferencePool
metadata:
  name: release-name
  namespace: default
  labels:
    app.kubernetes.io/name: release-name-epp
    app.kubernetes.io/version: "0.0.0"
spec:
  targetPorts:
      - number: 8000
  selector:
    matchLabels:
      app: "vllm-llama3-8b-instruct"
  endpointPickerRef:
    name: release-name-epp
    port:
      number: 9002

[nirrozenbaum]

@rahulgurnani thanks for the quick PR.
however I think it’s a bit trickier than current fix.
the thing is that v1 crd and v1alpha2 crd have few different fields, which are used for the same purpose.

v1 has targetPorts: number while v1alpha2 has targetPortNumber.

do you mind comparing inf pool template from v0.5.1 (in the release 0.5 branch) to latest to make sure we don’t miss anything?

[nirrozenbaum]

/ok-to-test

[kfswain]

@rahulgurnani thanks for the quick PR.

however I think it’s a bit trickier than current fix.

the thing is that v1 crd and v1alpha2 crd have few different fields, which are used for the same purpose.

v1 has targetPorts: number while v1alpha2 has targetPortNumber.

do you mind comparing inf pool template from v0.5.1 (in the release 0.5 branch) to latest to make sure we don’t miss anything?

Also, the v1alpha1 inferencepool api is in the x-k8s.io group. So I'm not sure that this will successfully apply as is.

[rahulgurnani]

@rahulgurnani thanks for the quick PR. however I think it’s a bit trickier than current fix. the thing is that v1 crd and v1alpha2 crd have few different fields, which are used for the same purpose.

v1 has targetPorts: number while v1alpha2 has targetPortNumber.

do you mind comparing inf pool template from v0.5.1 (in the release 0.5 branch) to latest to make sure we don’t miss anything?

Sure @nirrozenbaum , I updated the PR to accommodate for this, PTAL.

The current output:

$~/gateway-api-inference-extension/config/charts/inferencepool$ helm template .  --debug --set  inferencePool.apiVersion=inference.networking.x-k8s.io/v1alpha2
...
---
# Source: inferencepool/templates/inferencepool.yaml
apiVersion: inference.networking.x-k8s.io/v1alpha2
kind: InferencePool
metadata:
  name: release-name
  namespace: default
  labels:
    app.kubernetes.io/name: release-name-epp
    app.kubernetes.io/version: "0.0.0"
spec:
  
  targetPortNumber:
      - number: 8000
  
  selector:
    matchLabels:
      app: "vllm-llama3-8b-instruct"
  endpointPickerRef:
    name: release-name-epp
    port:
      number: 9002

[kfswain]

Is this output from a helm dry run?

Do you mind actually applying it to a cluster that had both versions of the CRD installed?

Helm doesn't do any validation against CRD definitions

[kfswain]

/retest

[nirrozenbaum]

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: nirrozenbaum, rahulgurnani

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:

• OWNERS [nirrozenbaum]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment