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
- [DSV4.1] Support decoder SWA bounded replay with vision CP and DSpark
- [DeepSeek-V4.1] Sparse prefill group sharing
- [unified-memory] trtllm_mha on the unified pool: decode graphs and speculative decoding
- [ROCm] Reject silent explicit FA fallback
- [Docs] Add missing schedule-policy options
- MLU CI Reliability Tracking
- [LoRA] Honor PEFT use_rslora scaling
- [MPS] Add capability-checked compiled MLX decode for Torch-owned models
- Fix/intern lm 2
- [LoRA] Support GPT-OSS MXFP4 experts with Marlin
- Docs
- Python not yet supported