clean up: remove model server type

[capri-xiyue]

What type of PR is this?

/kind cleanup

What this PR does / why we need it:
As #2161 merged, we no longer need model server type in helm chart as such info is now exposed via model server deployment via label inference.networking.k8s.io/engine-type
Which issue(s) this PR fixes:

Fixes #

Does this PR introduce a user-facing change?:

No more `inferencePool.modelServerType` in `inferencepool` helm chart  and `standalone` helm chart and no more `inferenceExtension.endpointsServer.modelServerType` in `standalone` helm chart

[netlify]

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

Name	Link
🔨 Latest commit	8d8829e
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/698b8756e0278d0008ff7a6a
😎 Deploy Preview	https://deploy-preview-2311--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.

[capri-xiyue]

I deleted it as because such config should just be done by setting model server deployment labels and it has been covered in other docs in https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/site-src/implementations/model-servers.md

[capri-xiyue]

/assign @ahg-g

[capri-xiyue]

/assign @kfswain

[kfswain]

/lgtm
/approve

Thanks @capri-xiyue !

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: capri-xiyue, kfswain

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

The pull request process is described here

Details

Needs approval from an approver in each of these files:

• OWNERS [kfswain]

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

[ahg-g]

Actually we have to revert this. while #2161 is merged, it is behind the datalayer feature flag, which is disabled by default. The multi-engine support is implemented as part of the metrics datalayer plugin, not the legacy metrics collection path which unfortunately is still the default and relies on the command line flags.