[Metrics] Add grafana dashboard for Inference extension and vLLM metrics

[JeffLuoo]

Dashboard preview:

Load dashboard using json file: https://grafana.com/docs/grafana/latest/dashboards/build-dashboards/import-dashboards/#import-a-dashboard

[k8s-ci-robot]

Hi @JeffLuoo. Thanks for your PR.

I'm waiting for a kubernetes-sigs 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.

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.

[JeffLuoo]

@liu-cong @ahg-g @courageJ

[netlify]

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

Name	Link
🔨 Latest commit	ab7b2ed
🔍 Latest deploy log	https://app.netlify.com/sites/gateway-api-inference-extension/deploys/67a132bc659aac0009507692
😎 Deploy Preview	https://deploy-preview-237--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 site configuration.

[ahg-g]

/ok-to-test

[danehans]

@JeffLuoo can you provide the steps to reproduce the dashboard?

[JeffLuoo]

Hi @danehans I added the instruction of uploading json dashboard to grafana in the description of the PR. To deploy Prometheus and configure Prometheus to collect metrics, there are different ways to do it and I can add that instruction in another change to focus on the instruction.

[danehans]

@JeffLuoo I am trying to test this PR. What is your Slack handle so I can ping you with specific questions instead of polluting this PR?

[JeffLuoo]

@danehans I just ping you in slack.

[danehans]

@JeffLuoo

gateway-api-inference-extension/examples/dashboards/inference_gateway.json

Line 1345 in e9f2de7

"value": "deap2an4eadc0d"

still needs to be replaced with ${DS_PROMETHEUS}.

[ahg-g]

I would move this under the tools not examples.

[danehans]

I'm also working with @JeffLuoo to repro the dashboard in my test environment.

[JeffLuoo]

Hi @danehans, I think that's the value of dashboard in the templating. When you load the dashboard, it will be automatically replaced with the id of your data source. I replace it with ${DS_PROMETHEUS} or just empty string, it is still configured to my datasource automatically.

[JeffLuoo]

@ahg-g Moved it to /tools

[danehans]

Great work on this! 🎉 I was able to successfully reproduce the dashboard in my test environment and configured Prometheus to scrape vLLM metrics. Now, I can see the "Token Throughput" and other metrics appearing in the dashboard.

However, shouldn't these metrics be displayed under the "vLLM" tab? Currently, I see 0 panels for both the InferencePool and vLLM tabs.

Additionally, could you provide more information about the InferencePool tab? Are these metrics sourced from Envoy, or do they come from another component?

Thanks again for your hard work—this is a great addition! 🚀

[JeffLuoo]

@danehans Moved panels related to vLLM under vLLM row.

Remove the row for inference pool as metrics for inference pool is not yet implemented.

[ahg-g]

/lgtm
/approve

Thanks @JeffLuoo !

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

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

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