docs(proxy): document --max_requests_before_restart_jitter#367
Merged
Conversation
Adds the new jitter flag to the proxy CLI reference and to the production worker-recycling guide, where staggering restarts to avoid synchronized worker recycling is the relevant production concern. Covers the uvicorn>=0.41.0 requirement and that the flag has no effect without --max_requests_before_restart. Documents BerriAI/litellm#30601
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Documents the new
--max_requests_before_restart_jitterproxy flag added in BerriAI/litellm#30601.The CLI reference (
docs/proxy/cli.md) gets a flag entry next to--max_requests_before_restart, covering the env var, the uvicorn (limit_max_requests_jitter, requires uvicorn>=0.41.0) and gunicorn (max_requests_jitter) mappings, and that it has no effect without a base restart threshold.The production guide (
docs/proxy/prod.md) gets a short paragraph in the worker-recycling section explaining the synchronized-restart problem; when several workers boot together they recycle in lockstep and drop a chunk of capacity at once, and the jitter flag staggers those restarts. This is the production concern that motivated the feature.Type
📖 Documentation