Skip to content

Conversation

JaredforReal
Copy link
Contributor

@JaredforReal JaredforReal commented Oct 3, 2025

Add reasoning rate & cost & refusal rates to the Grafana dashboard to get the issue done and provide more insightful data for the User.
Which issue(s) this PR fixes:

Fixes #48

Copy link

netlify bot commented Oct 3, 2025

Deploy Preview for vllm-semantic-router ready!

Name Link
🔨 Latest commit 8fa851e
🔍 Latest deploy log https://app.netlify.com/projects/vllm-semantic-router/deploys/68e098894daab200088af50a
😎 Deploy Preview https://deploy-preview-327--vllm-semantic-router.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

Copy link

github-actions bot commented Oct 3, 2025

👥 vLLM Semantic Team Notification

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

📁 deploy

Owners: @rootfs, @Xunzhuo
Files changed:

  • deploy/kubernetes/observability/grafana/configmap-dashboard.yaml
  • deploy/llm-router-dashboard.json

vLLM

🎉 Thanks for your contributions!

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

@rootfs
Copy link
Collaborator

rootfs commented Oct 3, 2025

@JaredforReal can you post a screenshot?

Signed-off-by: JaredforReal <[email protected]>
@JaredforReal
Copy link
Contributor Author

JaredforReal commented Oct 4, 2025

image I think I need to find some prompt to trigger refusal from model

Copy link
Member

@Xunzhuo Xunzhuo left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks

@rootfs rootfs merged commit e54d751 into vllm-project:main Oct 4, 2025
15 checks passed
@JaredforReal JaredforReal deleted the grafana branch October 4, 2025 15:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[v0.1] Observability: Minimal operator dashboard
3 participants