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] Add support for HunyuanImage-3.0-Instruct
- Require exactly one generation input type
- [diffusion] feat: support out-of-tree platforms and hook plugins
- [Fix] Honor metrics content negotiation in gRPC sidecar
- [Spec] Enable draft-extend CUDA graph on FlashAttention (fa3) via backend capability
- perf: cache constant DP-attention fallback tensor across iterations
- [HiSparse] Fix layer indexing and enable prefetch under PP
- fix: preserve canonical config actions with deprecated aliases
- [Fix][Spec] TRTLLM-MHA draft-extend graph replay races req_to_token writes; defer WAR read-done via a dedicated capability
- [Model] Add SKT A.X-K2 and ModelOpt NVFP4 support
- Docs
- Python not yet supported