Update best practices for num_workers

[berri-teddy]

Title

Add num_workers CPU matching best practice to production documentation

Relevant issues

N/A

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

📖 Documentation

Changes

This PR addresses a gap in the production best practices documentation by adding crucial guidance on num_workers optimization.

• Why: The documentation was missing a key best practice: matching num_workers to the CPU count for LiteLLM Proxy can significantly boost performance (up to +400 RPS). This change ensures users are aware of this optimization and how to implement it.
• What: A new section "3. Set num_workers to match CPU count for optimal performance" has been added to docs/my-website/docs/proxy/prod.md. This section details the performance benefits, default behavior, and configuration options. Subsequent sections were renumbered to maintain proper order.

---

Slack Thread

 

[cursor]

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
_{Learn more about Cursor Agents}

[vercel]

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

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Error			Sep 25, 2025 9:59pm

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}