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][KDA] Rebuild accepted-state lists during CUDA graph capture
- [UT][NPU] Add unit tests for npu quantization modules
- fix(kda): route NVIDIA prefill padding to the reserved Mamba slot
- [Spec] Fix DSpark shared-read ordering under overlap
- Move VL routing into MoE layers
- [AMD][DI][HiCache] Size the HiCache host budget from hugepages
- Add TraceLab session replay benchmark
- Hicache fixed
- [Bugfix] Respect parameterized SwiGLU in contiguous DeepGEMM MoE
- [Bugfix] Support MiniMax-M3 with MegaMoE
- Docs
- Python not yet supported