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] Keep profiler state consistent across start/stop requests
- [Docs] Clarify Ascend NPU graph capture fallback
- fix: reject duplicate client supplied bootstrap room
- Pr dsv4 flash test case
- [HiCache] Do not shrink full L3 prefetch hits to available host capacity
- [Fix] Validate step limits for stage-based profiling
- [NPU] Capture DeepSeek-V4 state block table construction in NPUGraph
- fix: prevent Q8 attenuation for low amplitude BF16 all-reduce inputs
- [Responses] Route expanded generation turns through a PD gateway
- fix: resolve issue 40083 by adding regression tests
- Docs
- Python not yet supported