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
- [rust-renderer] Run http feature tests and clippy in CI
- fix(hicache): consume the pending CUDA error when host registration fails
- [PD][NIXL] Recover live peers after remote disconnects
- [Feature] Jamba 1.5 Support PLS
- Extensive benchmarking of reasoning models including variance
- [Feature] Qwen3 Provide Ability to Turn off Thinking on server startup
- [Bug] Mllama ambiguous multi-image behaviour
- [Tracking] Improve Multimodal CI coverage
- Refactor,Extract Common Functionality into BaseCausalLM Abstract Class
- Allow larger max num dispatch tokens per rank for DeepEP
- Docs
- Python not yet supported