# SGLang 0.5.22 adds faster models and Apple Silicon support

> The open‑source inference engine upgrades to version 0.5.22, boosting throughput for several models and adding native Mac support.

Oossa · 2026-10-19 · https://oossa.com/en/sglang-0-5-22-adds-faster-models-and-apple-silicon-support

The SGLang project released version 0.5.22. It speeds up DeepSeek‑V4.1 by up to 2.3× on NVIDIA H200 GPUs and adds AMD MI350X/MI355X support with up to 1.9× throughput. New models such as EmbeddingGemma 2 and Kandinsky 6 are now included. The engine can now run on Apple Silicon Macs using the standard PyTorch backend. Upgrading requires Python 3.11 or newer.

## The facts

- Release date: Mon Oct 19 2026
- DeepSeek‑V4.1 up to 2.3× faster on H200, 1.9× on AMD MI350X/MI355X

## Why it matters

Developers can run larger LLMs faster on more hardware, including Macs, without buying new servers.

## Sources & references

1. [sgl-project/sglang v0.5.22](https://github.com/sgl-project/sglang/releases/tag/v0.5.22) – SGLang, 2026-10-19

Last updated: 2026-10-19