fix: update RBAC and mirror InferencePool with v1alpha2 API version

[chewong]

Follow-up for #1071. The dev release of the reference EPP implementation has transitioned to using InferencePools with API vesrion inference.networking.k8s.io/v1 but most Gateway providers are lagging behind and still using inference.networking.x-k8s.io/v1alpha2. For example, when testing with Istio Gateway + inference.networking.k8s.io/v1:

---

This PR attempts to temporarily fix the issue by mirroring the exact InfernecePool resource from v1 to v1alpha2 in the Helm chart so both the reference EPP and Gateway that hasn't adopted inference.networking.k8s.io/v1 can work well with each other.

Testing:

# install inferencepool + epp deployment via helm
helm install workspace-llama-3-1-8b-instruct config/charts/inferencepool -f values.yaml

# modify HTTPRoute to use InferencePool from inference.networking.x-k8s.io/v1alpha2

kubectl get svc
NAME                                          TYPE           CLUSTER-IP
inference-gateway-istio                       LoadBalancer   10.0.134.160

kubectl run -it --rm --restart=Never curl --image=curlimages/curl -- curl -X POST http://10.0.134.160/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-8b-instruct",
    "messages": [{"role": "user", "content": "What is kubernetes?"}]
  }'| jq
If you don't see a command prompt, try pressing enter.
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "**What is Kubernetes?**\n\nKubernetes (also known as K8s) is an open-source container orchestration system for automating the deployment, scaling, and management of containerized applications. It was originally designed by Google, and is now maintained by the Cloud Native Computing Foundation (CNCF).\n\n....",
        "reasoning_content": null,
        "role": "assistant",
        "tool_calls": []
      },
      "stop_reason": null
    }
  ],
  "created": 1753989500,
  "id": "chatcmpl-a49c3b08-b64a-4051-b77e-7d04d5f02304",
  "kv_transfer_params": null,
  "model": "llama-3.1-8b-instruct",
  "object": "chat.completion",
  "prompt_logprobs": null,
  "usage": {
    "completion_tokens": 671,
    "prompt_tokens": 40,
    "prompt_tokens_details": null,
    "total_tokens": 711
  }
}

This PR also adds the missing read-only RBAC for InferencePools in inference.networking.k8s.io.

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: chewong
Once this PR has been reviewed and has the lgtm label, please assign danehans for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS

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

[netlify]

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

Name	Link
🔨 Latest commit	cc85672
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/688bc2de0018780008c3de8a
😎 Deploy Preview	https://deploy-preview-1274--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.