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] Decode HiCache reports host and storage cache hits as device hits
- [Fix] humming: correct local work estimates for EP tuning
- [Feature] Accept `reasoning_content` and `join` in response templates
- [Fix] qwen3-coder: Recover unescaped inner quotes in JSON parameters
- [Fix] mimo: Preserve ModelOpt policies for packed projections
- [Fix] disaggregation: Attribute decode HiCache hits to host and storage
- [Fix] Z-Image: Correct and optimize Ulysses sequence layout
- [CI] [AMD] miles: Keep /root/models and /root/datasets on /sgl-data
- [Perf] diffusion: enable H3 Image FP8 attention on DGX Spark
- [Feat] function_call: Add granite_toolcall_parser for Granite 4.2
- Docs
- Python not yet supported