feat: add LLM-D profile for E2E testing framework

[samzong]

FIX #658 (link existing issues this PR will resolve)

LLM-D profile e2e

Summary

Add an LLM‑D e2e profile to validate LLM-based decision routing in a standard K8s/Kind environment, with focus on correctness, resilience, and basic observability.

What's changed

• Added LLM-D profile under e2e/profiles/llm-d/ (install, config, health checks, cleanup), selectable via E2E_PROFILE=llm-d.
• Registered the LLM-D profile in e2e/cmd/e2e/main.go so it is managed through the unified e2e entrypoint.
• Hooked the existing core e2e suites (routing, failover, multi‑replica serving, health/readiness, basic performance) to also run against the llm-d deployment.
• Updated .github/workflows/integration-test-k8s.yml to include E2E_PROFILE=llm-d in the k8s integration test matrix.
• Updated tools/make/e2e.mk and e2e/README.md with LLM-D usage, examples, and basic troubleshooting.
• Added a short stabilization window and explicit health checks to reduce flakiness on Kind/CI clusters.

How to run

• Setup only: make e2e-setup E2E_PROFILE=llm-d
• Run tests: make e2e-test E2E_PROFILE=llm-d
• Optional verbose logs: make e2e-test E2E_PROFILE=llm-d E2E_VERBOSE=1

[netlify]

✅ Deploy Preview for vllm-semantic-router ready!

Name	Link
🔨 Latest commit	189754b
🔍 Latest deploy log	https://app.netlify.com/projects/vllm-semantic-router/deploys/6926d7c3af82ff00087167d7
😎 Deploy Preview	https://deploy-preview-705--vllm-semantic-router.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.

[github-actions]

👥 vLLM Semantic Team Notification

The following members have been identified for the changed files in this PR and have been automatically assigned:

📁 e2e

Owners: @Xunzhuo
Files changed:

• e2e/profiles/llm-d/manifests/httproute-services.yaml
• e2e/profiles/llm-d/manifests/inference-sim.yaml
• e2e/profiles/llm-d/manifests/rbac.yaml
• e2e/profiles/llm-d/profile.go
• e2e/profiles/llm-d/values.yaml
• e2e/README.md
• e2e/cmd/e2e/main.go

📁 Root Directory

Owners: @rootfs, @Xunzhuo
Files changed:

• .github/workflows/integration-test-k8s.yml

📁 tools

Owners: @yuluo-yx, @rootfs, @Xunzhuo
Files changed:

• tools/make/e2e.mk

---

🎉 Thanks for your contributions!

This comment was automatically generated based on the OWNER files in the repository.

[samzong]

@Xunzhuo It's ready for review.

[Xunzhuo]

Cool, a quick question, any test cases for features combine VSR features and llm-d ?

[samzong]

@Xunzhuo Yes

• VSR => Auto routing: e2e/testcases/llmd_auto_routing.go
• LLM-d => Distributed inference: e2e/testcases/llmd_distributed_inference.go

[samzong]

/gemini summary

[samzong]

@Xunzhuo @rootfs

Hi, I've add details with "What's Changed" and "TestCases".

Could you please review it and let me know if there are any other issues?

[Xunzhuo]

My question is looking at the testcases they are around the functionality of llm-d, that is good but the integration test should add more cases around vsr + llm-d like verifying model auto selection + llm-d, ideally should reuse the shared test cases

[samzong]

@Xunzhuo Thanks for the review.

I will add VSR + LLM-D integration tests, reuse existing VSR auto-routing cases, verify selected-model consistency with the LLM-D backend, and include the failover path.

[samzong]

update: all use shared testcase.

================================================================================
TEST RESULTS
================================================================================
✅ PASSED - chat-completions-request (2.143574634s)
✅ PASSED - chat-completions-stress-request (20.746133879s)
✅ PASSED - chat-completions-progressive-stress (22.525980752s)
✅ PASSED - domain-classify (1m15.987869552s)
================================================================================
Total: 4 | Passed: 4 | Failed: 0
================================================================================
[Runner] 📝 Collecting semantic-router logs...
[Runner] ✅ Semantic router logs saved to: semantic-router-logs.txt
[Runner] ✅ All tests passed!

[samzong]

@Xunzhuo Now it has been processed, llmd_* testcases have been removed. all cases have been reused, and has test passed.

[Xunzhuo]

very cool. Thanks