Published collection
SGLang and Miles support Qwen3.8 on day one
Day-one support from inference and serving frameworks can speed up deployment of large open-source Qwen models.
- Published entries
- 1
- Sources
- 1
- Date range
- 2026-08-13
- Primary labels
- Models · 模型 · Open-source models · Qwen3.8-2.4T-A95B · 阿里千问
Published evidence
Every entry keeps its summary and a path back to the source context.
SGLang and Miles support Qwen3.8 on day one
SGLang and Miles supported Qwen3.8-2.4T-A95B on launch day; the model is Qwen’s largest open-source model, with 2.4T total parameters, 95B active per token, and a hybrid attention architecture.
Original source