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
- [api_server] Plumb runtime multimodal kwargs
- [HiSparse][ROCm] Use TileLang NSA backend policy on HIP
- [Speculative] Support topk>1 in adaptive speculative decoding
- [MoE] Add fused MoE auto tune CLI
- [vlm][pixtral] support precomputed embeddings + processor output
- Fix Qwen3 Coder streaming string arguments
- Fix: handle callNNNNN tool call IDs in KimiK2Detector
- feat(observability): add chunked prefill trace attributes
- [3/4][LoRA] Improve NVFP4 Cutlass MoE combine accuracy
- [4/4][LoRA] Add NVFP4 Cutlass LoRA virtual experts
- Docs
- Python not yet supported