feat: Configure LRUCacheSize using the numGPUBlocks for approximate prefix cache

[zetxqx]

What type of PR is this?

/kind feature

What this PR does / why we need it:
This change introduces the ability to configure the numGPUBlocks for the approximate prefix cache.

Key changes:

• The indexer now considers numOfGPUBlocks from the server's metrics when creating a new LRU cache. This allows the cache size to be dynamically adjusted based on the server's capacity.
• If numOfGPUBlocks is not available, a default LRU size is used.
• The Add method in the indexer now accepts a Server struct, which includes both the ServerID and numOfGPUBlocks.

Which issue(s) this PR fixes:

Fixes partially #1304
Fixes #1512

Does this PR introduce a user-facing change?:

feat: configure LRUCacheSize using the numGPUBlocks for approximate prefix cache scorer

[netlify]

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

Name	Link
🔨 Latest commit	920ac60
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/68f2fcd7be892c0008e5c1c8
😎 Deploy Preview	https://deploy-preview-1748--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.

[zetxqx]

/assign @liu-cong

[liu-cong]

/lgtm

[zetxqx]

cc: @kfswain @ahg-g @nirrozenbaum can you take a look for the approval?

[ahg-g]

Will this work with sglang? and generally, will this introduce a regression if the model server doesn't emit this metric?

[liu-cong]

Will this work with sglang? and generally, will this introduce a regression if the model server doesn't emit this metric?

If metrics is not available, the default configuration will continue to be used (current behavior), so no regression.

[ahg-g]

/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: ahg-g, zetxqx

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 [ahg-g]

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