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] PP+PD: Fix consensus checker failure while using PP prefill
- [Fix] [CPU] Fix: Qwen3.5-35B-A3B-GPTQ-Int4 quantization rule failure and accuracy degradation
- [Perf] paged-experts: fewer host syncs in host-planned steps
- [Roadmap] TDX/CC Prefill–Decode Disaggregation
- [Fix] diffusion: LingBot QKV sharing, causal RoPE on no-cache path, uneven split guard
- [Fix] responses: Align K3 input token usage with Chat
- [Fix] diffusion: fix 11 quantization-layer correctness bugs (MXFP4, FP8, KitchenW4A4, Nunchaku)
- [Fix] scheduler: Publish KV events while the engine is paused
- [Perf] scheduler: Track num_held_rows incrementally in prefill batch admission
- [Feat] nvfp4: Support phase-selective W4A16 and per-token scaling
- Docs
- Python not yet supported