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
- [MoonEP] Kimi-K3 production integration roadmap
- [BugFix] Honor quant_config in Qwen3-Omni audio encoder layers
- [PD] Bound mooncake failed-session blacklist with a TTL
- [Diffusion] Add configurable reference image resizing for MiniMax H3 Ref2VA
- fix(qwen3-omni/asr): support heterogeneous audio lengths in cross-request MM batches
- [Bug] Qwen 3.8 27b NVFP4 incorrect coordinate detection on image
- [NPU] Adapt DeepSeek-OCR-2 multimodal OCR model on Ascend NPU
- [Bug] NVFP4 KV cache + speculative decoding: extend_prefix_lens_cpu is None in the dequant workspace path
- [Attention] Fix NVFP4 speculative decoding with TRTLLM MHA
- fix: make FlashInfer NVFP4 speculative decoding graph-safe
- Docs
- Python not yet supported