# vLLM v0.22.1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.22.1
- **Released:** Jun 05, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.22.1/

## Executive Summary (TL;DR)
vLLM v0.22.1. Source highlight: This release features 8 commits from 6 contributors (1 new)!

## Improvements
- **AMD Zen CPUs**: route W8A8 (int8 dynamic-symmetric) and W4A16 (GPTQ) linear inference through zentorch kernels, registered ahead of the generic oneDNN CPU kernels, with transparent fallback on non-Zen CPUs, GPUs, and XPU (#41813).

## Bug Fixes
- Fix `OlmoHybridForCausalLM` failing to initialise after the checkpoint changed `rope_parameters` from `None` to `{"rope_type": None}` (#43846).
- Fix **HyperCLOVAX** loading after the upstream HuggingFace repo removed its remote code (now native in `transformers >= 5.9.0`): register the `hyperclovax` model_type so vLLM uses its vendored config instead of the stale `auto_map` (#43860).
- Fix a deterministic hang in multi-node **Ray data-parallel** serving with `num_api_servers > 1` by excluding the Ray DP backend from the deferred (kernel-assigned) port allocation introduced in #42585 (#43864).

## Upgrade Command
```bash
python -m pip install 'vllm==0.22.1'
```