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 replicated (TP1) shared expert being summed by collectives that skip the MoE all-reduce
- [Scheduler] Stop waiting-queue scan after chunk budget exhaustion
- [Fix][GDN] Route DFlash/DSpark commits through ReplaySSM spec fold
- Use model-native video preprocessing for Qwen3-VL
- [CUDA] Add dense and MoE GGUF MMQ kernels for eight I-quant types
- [PD] Propagate stable request ID across prefill and decode workers
- [HiCache] Support Mamba in buffer-only host memory mode
- [NPU] Add ModelSlim MoE prefix regression tests
- [NPU] Use Native mrope
- [Observability] Add --log-schedule-decisions and include pid in scheduler log prefix
- Docs
- Python not yet supported