diff --git a/berkeley-function-call-leaderboard/README.md b/berkeley-function-call-leaderboard/README.md
index e4a200ebe..6c749647c 100644
--- a/berkeley-function-call-leaderboard/README.md
+++ b/berkeley-function-call-leaderboard/README.md
@@ -208,6 +208,7 @@ Some companies have proposed some optimization strategies in their models' handl
 
 ## Changelog
 
+* [July 20, 2024] [#537](https://github.com/ShishirPatil/gorilla/pull/537): Update generation script for locally-hosted OSS model to use single-node multi-GPU inference method (tensor parallel). Ray is not used anymore.
 * [July 16, 2024] [#525](https://github.com/ShishirPatil/gorilla/pull/525), [#536](https://github.com/ShishirPatil/gorilla/pull/536): Add new model `ibm-granite/granite-20b-functioncalling` to the leaderboard.
 * [July 10, 2024] [#522](https://github.com/ShishirPatil/gorilla/pull/522): Bug fix in the evaluation dataset for Executable Parallel Multiple category. This includes updates to both prompts and function docs. 2 entries are affected.
 * [July 8, 2024] [#516](https://github.com/ShishirPatil/gorilla/pull/516): Fix double-casting issue in `model_handler` for Java and JavaScript test categories.