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] Preserve Pythonic tool calls and trailing text across streaming chunks
- Fix Qwen3.5 MTP partial MXFP4 quantization
- [Bug] VisionFlash4Attention drops MiMo-style window attention and sinks
- Fix FA4 vision attention window sinks
- [REFACTOR][SenseNova] Fix PR 36606 review issues and preserve lazy SenseNova imports
- fix(multimodal): manage auxiliary patch feature transport and lifetime
- fix(parser): preserve and recover Step tool calls across reasoning and XML parsing
- [Fix] Honor DSpark SPS profiler budget pins and handle ragged mRoPE positions
- [Bug] DSpark compact SPS profiling ignores forced budgets and fails on ragged mRoPE positions
- [Qwen4] Release loader parameter snapshot before quantization post-processing
- Docs
- Python not yet supported