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
- [Bug] Prefill input logprobs are served from the wrong request when a batch member is retracted or finished
- fix(mimo-v2): reduce audio encoder attention over the attn-TP group
- [Bug] GLM-5.3-Flash on RTX PRO 6000 (sm_120): two DSA backend blockers after the deep_gemm NameError
- [Score API] Support caller-supplied rid on score requests
- [Kernel] Add per-layer LF-to-PF KV transfer for LayerSplit HiCache
- docs: add Simplified Chinese translation (README.zh.md)
- [QSA] Tune sm120 sparse prefill geometry
- [Bug] NEXTN/MTP draft acceptance decays to ~0 over server uptime on qwen4_exp (Qwen3.8-Flash-Next), fully restored by a restart
- [Bug] Kimi-K3 tool_choice=required requests hang until ReadTimeout in 2P2D TP8/DCP8 deployment
- [VLM] Redact multimodal inputs from load errors
- Docs
- Python not yet supported