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
- [Feature] Accept multiple API keys via comma-separated --api-key
- [Fix] Honor iteration settings in fused collective benchmark
- test(npu): run GLM-5.2 gpqa in nightly
- Fix generic Transformers-fallback multimodal path for Chameleon and Fuyu
- [Fix] GLM detectors: streamed tool-call arguments disagree with non-streaming
- [Bug] gemma-3n-E2B-it/E4B-it: degenerate output (fa3/flashinfer) or crash (triton) in multimodal serving, 0% vision accuracy
- [Fix] step3: parameterless tool calls are dropped, batched calls get mixed up
- [Mamba][Fix] Register a split node under its own key in the mamba radix cache
- [Bug] DeepSeek-V4-Flash-0731 fails to stop at stop sequence when preceded by Chinese text
- [PD][NIXL] Prevent abort ACK with unresolved errored transfers
- Docs
- Python not yet supported