SLO Aware Routing PD Disaggregation Support

[RishabhSaini]

Add PD Mode Support for Dual Latency Predictors

Extends inferencepool Helm chart to support separate latency predictors for prefill and decode pods in PD disaggregated scheduling.

Architecture: Deploys 4 sidecars per EPP pod:

• Prefill training server (port 8000) + prediction server (port 8001)
• Decode training server (port 8010) + prediction server (port 8011)

Each predictor trains and predicts independently: prefill predicts TTFT for prompt processing, decode predicts TTFT+TPOT for token generation. Auto-generates environment variables (PREFILL_TRAINING_URL, DECODE_TRAINING_URL, etc.) consumed by llm-d-inference-scheduler for SLO-aware joint optimization.

Fully backward compatible with legacy single-predictor mode (default).

Links to related PRs:
llm-d/llm-d#442
llm-d/llm-d-inference-scheduler#511

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

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

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

Details

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	d9556ef
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/693c795dc72e6a000871063b
😎 Deploy Preview	https://deploy-preview-1993--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 @RishabhSaini. Thanks for your PR.

I'm waiting for a github.com 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.

Details

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.