sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [Docs] Add Qwen3 Ascend recipes and measured A3/A2 results
- [Feature] Add constrained per-request DSpark draft LoRA support
- [Diffusion] Add SenseNova U1 thinking mode
- [NPU] Fix MoE none EP routing and draft backend inheritance
- [Feature] Add FP8 SSM state pool (`--mamba-ssm-dtype float8`) for GDN hybrid models
- [ROCm][Perf] Route 512-expert softmax MoE routing through aiter topk_gating
- [Bugfix] Fix stale MiniMax-H3 attention test mock paths
- [Prefill Graph/Models] Support prefill graph for GDN/Mamba and Gemma models
- Support LogitsProcessorOutput and dataclass outputs in BreakableCudaGraphBackend
- [XPU] Stage serialized XPU tensors through host shared memory
- Docs
- Python not yet supported