SGLang
High-performance serving framework for large language and multimodal models.
Local inference
Open SGLang in AirStackWhat SGLang’s own pages say
| What it says it does | High-performance serving framework for large language and multimodal models. docs.sglang.io |
|---|---|
| Platforms | AMD, Ascend NPU, Google TPU, Intel Xeon, Moore Threads MUSA, NVIDIA, Moore Threads MUSA accelerators docs.sglang.io |
| Integrations | Hugging Face, OpenAI APIs docs.sglang.io |
| Open source | Yes docs.sglang.io |
| Models supported | Llama, Qwen docs.sglang.io |
Each value is a quote AirStack found on the product’s own pages, read 2026-11-04. A missing field means AirStack has not found it on its pages.