Rename the PodMetrics type

[ahg-g]

Perhaps we can name it Endpoint

[kfswain]

I like ModelServerPod and then Metrics as a field of the struct. But I feel more strongly that we move away from PodMetrics than I do towards a specific name (so long as that name is an improvement.)

Let the Great Name Wars commence! 😆

[ahg-g]

Nit: in a multi-node setup, the server is not just a pod, it is a group of pods. While we could say that we only care about the single pod representing the group (aka the leader), an endpoint might be more generic here especially if we name the extension "Endpoint Picker".

[hzxuzhonghu]

The InferencePoolSpec.Selector documented to select model server pods, so how about ModelServerStats

[ahg-g]

ModelServer alone is another one?

I generally think this item is lower priority compared to increasing test coverage though.

[k8s-triage-robot]

The Kubernetes project currently lacks enough contributors to adequately respond to all issues.

This bot triages un-triaged issues according to the following rules:

• After 90d of inactivity, lifecycle/stale is applied
• After 30d of inactivity since lifecycle/stale was applied, lifecycle/rotten is applied
• After 30d of inactivity since lifecycle/rotten was applied, the issue is closed

You can:

• Mark this issue as fresh with /remove-lifecycle stale
• Close this issue with /close
• Offer to help out with Issue Triage

Please send feedback to sig-contributor-experience at kubernetes/community.

/lifecycle stale