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
- [Sepc]Dflash2 tree drafting
- fix(mlx): prevent CPU/MPS device mismatch in FutureMap
- [Kernel] Bound the EAGLE tree ancestor walk and stop when the ancestor is missing
- [RFC] Per-Token-Range KV-Cache Retention Priority
- Use FlashInfer router GEMM with JIT fallback
- feat: support temperature-scaled input logprobs
- fix(platform_stubs): import importlib submodules explicitly
- Fix two logging calls that raise TypeError instead of logging
- [Gateway] Preserve rid and secure control-plane credentials
- [AMD][DI][CI] 10.5/N Add DeepSeek-R1-0528 FP8 HiCache 1P1D nightly recipe
- Docs
- Python not yet supported