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
- [Bugfix] Preserve non-tool JSON responses in Llama32Detector and add exist_ok to qwen3_asr AutoConfig
- fix(health): abort the timed-out /health probe scheduler-side
- [SM12x] attention: b12x compressed-MLA branch for DSv4-Flash
- Add Kimi-K3 MLA support to DSpark drafts
- [Bug] `uv pip install sglang` with uv < 0.12 silently installs 0.5.9 (6 months old)
- Refactor TRTLLM MHA backend inheritance
- [MoonEP] Add zero-copy eager expert output path
- [MoonEP] Add single-flight async event chaining
- [diffusion] Fix unbounded A2A staging buffer growth across request sh…
- [Bugfix] Skip singleton grammar token sync
- Docs
- Python not yet supported