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
- Amd/deepseek v4 rebase main fix graph 0513
- fix(disagg): disable cuda graph correctly when running prefill
- [log] Support structured JSON output for inference stats logging
- [2/14] Expose true-on-policy serving arguments
- [5/14] Add TP-invariant math operations
- [9/14] Apply Qwen3 MoE true-on-policy model rules
- [10/14] Update on-policy wiring CLI and default tests
- [NPU] [MOE] Fix DeepEP dispatcher automatic dtype detection & add A5 mxfp8/mxfp4 support
- [2/N]Qwen3.5Opt: Add fused gate-sigmoid-mul-add kernel
- fix: recapture CUDA graphs for RL online weight updates
- Docs
- Python not yet supported