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
- [Refactor] scheduler: Move a retract's release work into RequestRetirer.retract
- [Chore] entrypoints: Remove unreachable return
- [Fix] gemma4: Keep closed bracket pairs in undelimited tool-call array elements
- [Fix] loads: Answer an unknown include section with 400 instead of 500
- [Fix] [Intel] quantization: Serve GLM-4.7-Flash int4 AutoRound and Ling-3.0-flash-VL-fp4 on XPU
- [Perf] [NVIDIA] attention: Reduce head72 value accumulation on SM120
- [Bug] sgl-kernel: FA3 kernels are compiled and linked twice (hdimdiff sm90 and softcapall sm80 files)
- [Fix] sgl-kernel: Do not compile FA3 instantiation files twice
- [Fix] speculative: Validate QSA draft window before loading weights
- [AMD][K3.1] Split the DSA prefill indexer for short extends and use FlyDSL logits
- Docs
- Python not yet supported