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
- [Fix] scheduler: Reserve member rows of beam leaders admitted in the same prefill
- [Fix] attention: Cover CUDA graph padding in verify state indices
- [Refactor] diffusion: normalize diffusers output layout in one place
- [sglang-miles] [Feat] RL: WeightBridge weight receiver driven by the scheduler loop
- [Attention] Add cuDNN attention backend (prefill only)
- [Feat] minimax-m3.1: Support DSpark on Hopper
- [Tracking] MiniMax-M3.1-Flash support
- [Doc] quantization: Add architecture page; scope contribution guide to workflow
- [Diffusion] Cache static text conditioning per request (Krea2 first)
- [Feat] gguf: Support Bolt E4B Q4_K_M checkpoints
- Docs
- Python not yet supported