SGLang v0.5.22 ships new model support and up to 2.3x throughput gains
SGLang has released v0.5.22, with its release notes stating the version covers 950 pull requests from 245 contributors. The release adds support for models including Clef / Clef Flash, PPLX-Decider v1 / v1.1, EmbeddingGemma 2, LLaDA2.2, HunyuanImage-3.0-Instruct and Kandinsky 6. The notes say DeepSeek-V4.1 gains up to 2.3x more throughput per GPU on H200 and now runs on AMD MI350X / MI355X with up to 1.9x throughput from DSpark, while GLM-5.3 can combine decode context parallelism with MTP for up to 2.1x faster decoding. The release also requires Python 3.11 or newer and deprecates options such as --enable-dp-attention, making it a breaking-change upgrade.
SGLang is a widely used open-source inference framework, and this release claims up to 2.3x more per-GPU throughput for DeepSeek-V4.1 on H200 plus new AMD MI350X / MI355X support, alongside breaking changes such as the Python 3.11+ requirement and deprecated flags.
Highlights
950 PRs from 245 contributors.
New models
| Model | Type | Cookbook |
|---|---|---|
| Clef / Clef Flash | LLM / VLM | link |
| PPLX-Decider v1 / v1.1 | LLM / VLM | link |
| EmbeddingGemma 2 | LLM / VLM | link |
| LLaDA2.2 | LLM / VLM | |
| HunyuanImage-3.0-Instruct | Diffusion | link |
| Kandinsky 6 / Kandinsky 6 SR | Diffusion | link |
| Wan-Animate-2 | Diffusion | link |
| SANA-Video 2.0 | Diffusion | link |
| LLaDA-Image / LLaDA-Image-Turbo | Diffusion |
Some source content is omitted. Continue reading on the original site.
#SGLang#DeepSeek-V4.1#Qwen3.8-Flash-Next#GLM-5.3#MiMo-V2.6-Pro#EmbeddingGemma 2#HunyuanImage-3.0-Instruct#Kandinsky 6#AMD Instinct MI350X#Apple Silicon