vLLM v0.22.1 发布：新增 Mellum v2 支持与 Zen CPU 优化

AI 摘要

vLLM 发布 v0.22.1 补丁版本，包含 8 个提交，来自 6 位贡献者。该版本新增对 JetBrains Mellum v2 模型的支持，并在 AMD Zen CPU 上通过 zentorch 加速量化线性推理，同时修复了多节点 Ray 数据并行服务、DeepSeek-V4 初始化等问题。

正文节选

## Highlights This release features 8 commits from 6 contributors (1 new)! v0.22.1 is a patch release on top of v0.22.0 with targeted bug fixes plus a couple of additions: new model support for JetBrains' Mellum v2, zentorch-accelerated quantized linear inference on AMD Zen CPUs, and fixes for multi-node Ray data-parallel serving, DeepSeek-V4 initialization, and a few model-loading regressions. ### Model Support * New model: JetBrains' **Mellum v2**, an open-weights Mixture-of-Experts

发布时间：2026-06-05 18:10

抓取时间：2026-08-02 00:23

来源机构：vLLM