Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

(feat) Speedup health endpoint #1023

Merged
merged 2 commits into from
Dec 6, 2023

Conversation

PSU3D0
Copy link
Contributor

@PSU3D0 PSU3D0 commented Dec 6, 2023

Users may continuously monitor the /health endpoint in order to send alerts when deployments go down. It's important that the speed of the /health endpoint does not scale linearly with the number of deployments.

This PR does two things.

  • Move health check code to it's own file.
  • Use asyncio.gather for all valid models, removing linear time scaling for health checking.

Copy link

vercel bot commented Dec 6, 2023

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback Dec 6, 2023 5:29am

@ishaan-jaff
Copy link
Contributor

can you add a ss of this endpoint working on a request where you set up the config.yaml

from concurrent.futures import ThreadPoolExecutor


logger = logging.getLogger(__name__)
Copy link
Contributor

Choose a reason for hiding this comment

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

what is the purpose of this logger

Copy link
Contributor

@ishaan-jaff ishaan-jaff left a comment

Choose a reason for hiding this comment

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

lgtm ! thanks for fixes

@ishaan-jaff
Copy link
Contributor

will merge in 24 hours

@ishaan-jaff ishaan-jaff merged commit a4cf4e7 into BerriAI:main Dec 6, 2023
2 checks passed
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.

2 participants