# vLLM v0.3.2 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.3.2
- **Released:** Feb 21, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.3.2/

## Executive Summary (TL;DR)
vLLM v0.3.2. Source highlight: This version adds support for the OLMo and Gemma Model, as well as `seed` parameter.

## New Features
- Add code-revision config argument for Hugging Face Hub
- [Test] Add basic correctness test
- Add warning to prevent changes to benchmark api server
- Add metrics to RequestOutput
- Add Gemma model

## Bug Fixes
- [Minor] Small fix to make distributed init logic in worker looks cleaner
- Fix `vllm:prompt_tokens_total` metric calculation
- [FIX] Fix beam search test
- [FIX] Add Gemma model to the doc

## Upgrade Command
```bash
python -m pip install 'vllm==0.3.2'
```