# vLLM v0.19.1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.19.1
- **Released:** Apr 18, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.19.1/

## Executive Summary (TL;DR)
vLLM v0.19.1. Source highlight: This is a patch release on top of `v0.19.0` with Transformers v5.5.3 upgrade and bug fixes for Gemma4:

## New Features
- Add Gemma4 Eagle3 support (#39450)

## Bug Fixes
- [Bugfix] Fix invalid JSON in Gemma 4 streaming tool calls by stripping partial delimiters (#38992)
- [Bugfix][Frontend] Fix Gemma4 streaming HTML duplication after tool calls (#38909)
- [Bugfix] Fix Gemma4 streaming tool call corruption for split boolean/number values (#39114)
- [Tool] adjust_request to reasoning parser, and Gemma4 fixes (#39027)
- [Gemma4][Bugfix]: Enable Gemma4ForCasualLM to load lora adapters correctly (#38844)
- [Bugfix] Fix Gemma4 tool parser converting bare null to string "null" (#39679)

## Upgrade Command
```bash
python -m pip install 'vllm==0.19.1'
```