v0.9.0.1

vllm-project/vllmv0.9.0.1May 30, 2025by github-actions[bot]

AI Summary

A patch release containing a critical bugfix for DeepSeek family models on NVIDIA Ampere and below.

Key Highlights

Bugfix: Fix FA2 MLA Accuracy Issue for DeepSeek family on Ampere and below.

Full Release Notes

This patch release contains important bugfix for DeepSeek family of models on NVIDIA Ampere and below (#18807) 

**Full Changelog**: https://github.com/vllm-project/vllm/compare/v0.9.0...v0.9.0.1