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][DI][CI] Seed the draft proposal distribution on the PD decode path
- fix(spec): support case-insensitive dspark in pipeline parallel validation
- [JIT] Clean up kernel headers: move runtime helpers, add once.h
- [Feature] Incremental chat-prompt processing: stop re-tokenizing the whole history on every turn
- [OpenAI] Incremental chat tokenization for multi-turn prompts
- [Multimodal] Free fast processor pool tensors before the pool closes
- [Fix] Strip drifted </parameter> markers in the qwen3_coder detector
- fix: separate LoRA benchmark server flags
- [model] HunYuan v1: restore q/k shape after per-head qk_norm
- [qwen 3.8 next] Reduce repeated overlap batch snapshot work
- Docs
- Python not yet supported