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] dsv41: Preserve rejected tool calls in history
- [Fix] attention: Keep shared-KV verify split partials in FP32
- [Fix] attention: Ignore inactive splits when merging split-KV verify outputs
- [Feat] step5: Support HiSparse
- [Bug] GPU-name-only MNNVL detection rejects OEM-named GB300 devices
- [Fix] distributed: Detect MNNVL fabric independently of GPU names
- fix: audio model fallback bugs in voxtral/midashenglm processors and mrope scheduling
- [Fix] openai: Parse required tool calls when no tool-call parser is set
- [NPU] fix pp hang on npu
- [Fix] metrics: Handle process CPU clock resets after restore
- Docs
- Python not yet supported