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
- [AMD] Add rocm7.2.3 support
- Add accuracy evals to GB200 nightly pipeline
- [DSV4] Fix continue_final_message prefill rendering
- Add adaptive decode polling threshold for disaggregation
- Add router terminal prefix affinity for DP-aware routing
- [feat] Add Qwen3 MoE true-on-policy SP/PP support
- [14/14] Cover CUDA-only stable top-k and RMSNorm knobs
- fix(spec): trim Spec V2 grammar output in PD disagg overlap decode (port #24082)
- [Bench] fix mmmu multi image
- [WIP] Fuse shared expert gate into a single Triton kernel for Qwen MoE
- Docs
- Python not yet supported