SGLang 0.5.22 adds Apple Silicon support with the PyTorch backend and an InstantTensor loader

The SGLang project published v0.5.22 on GitHub on October 19, 2026. The release notes say SGLang now runs on Apple Silicon Macs with the standard PyTorch backend, alongside MLX, that a new InstantTensor loader speeds up model loading, and that HiSparse now supports EAGLE and MTP for long-context serving with the KV cache in CPU memory. Newly supported models listed include Clef / Clef Flash, PPLX-Decider v1 / v1.1, EmbeddingGemma 2, Kandinsky 6 and SANA-Video 2.0. The notes say SGLang now requires Python 3.11 or newer, and describe a fix for hybrid linear models that could resume from wrong mamba states when speculative decoding and structured output were used together. USASI has not tested these changes.1

USASI. (2026, October 20). SGLang 0.5.22 adds Apple Silicon support with the PyTorch backend and an InstantTensor loader. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-22-released/

@misc{usasi_news_sglang_0_5_22_released,
  author = {{USASI}},
  title = {SGLang 0.5.22 adds Apple Silicon support with the PyTorch backend and an InstantTensor loader},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/sglang-0-5-22-released/}},
  note = {United States of America Superintelligence. Last updated 2026-10-20}
}