From 71ce338b2417e990c86f5e955a42da2373a5579c Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 6 Sep 2025 16:07:02 -0700 Subject: [PATCH] docs fix --- .../release_notes/v1.76.3-stable/index.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/docs/my-website/release_notes/v1.76.3-stable/index.md b/docs/my-website/release_notes/v1.76.3-stable/index.md index 933b5fe9aa4..0f997d6941a 100644 --- a/docs/my-website/release_notes/v1.76.3-stable/index.md +++ b/docs/my-website/release_notes/v1.76.3-stable/index.md @@ -51,6 +51,21 @@ pip install litellm==1.76.3 ## Major Changes - **Performance Optimization**: LiteLLM Proxy now achieves +400 RPS when using correct amount of CPU cores - [PR #14153](https://github.com/BerriAI/litellm/pull/14153), [PR #14242](https://github.com/BerriAI/litellm/pull/14242) + + By default, LiteLLM will now use `num_workers = os.cpu_count()` to achieve optimal performance. + + **Override Options:** + + Set environment variable: + ```bash + DEFAULT_NUM_WORKERS_LITELLM_PROXY=1 + ``` + + Or start LiteLLM Proxy with: + ```bash + litellm --num_workers 1 + ``` + - **Security Fix**: Fixed memory_usage_in_mem_cache cache endpoint vulnerability - [PR #14229](https://github.com/BerriAI/litellm/pull/14229) ---