# vLLM v0.2.5 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.2.5
- **Released:** Dec 14, 2023
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.2.5/

## Executive Summary (TL;DR)
vLLM v0.2.5. Source highlight: Optimize Mixtral performance with expert parallelism (thanks to @Yard1)

## New Features
- gqa added to mpt attn
- [Docs] Add notes on ROCm-supported models

## Improvements
- Optimize Mixtral performance with expert parallelism (thanks to @Yard1)

## Bug Fixes
- [BugFix] Fix input positions for long context with sliding window
- Fix peak memory profiling
- [BugFix] Fix input positions for long context with sliding window

## Upgrade Command
```bash
python -m pip install 'vllm==0.2.5'
```
