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
- [Diffusion] Bind accelerator before distributed initialization
- Support llguidance reasoning grammar
- [qwen3.5] perf: Skip the GDN qkvzba split kernel on single-token forwards
- [Spec][DSV4] perf: Fuse draft-extend SWA location translation
- docs: add DSpark deployment guide
- [AMD] Accept row-strided views in RMSNorm aiter path
- fix: publish fresh KV metrics after batch shrink
- [Bug] deepseek-v4-flash toolcall error runner_backend from marlin to flashinfer_mxfp4
- [Bug] Unrecognized configuration class <class 'sglang.srt.utils.hf_transformers.common._DeepseekV4ConfigAlias'>
- [PD Disagg][HiSparse] Treat the CPU KV buffer as RadixCache L1
- Docs
- Python not yet supported