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] XGrammarGrammarBackend._sanitize_structural_format` skips `optional`, `star`, `plus`, `repeat`, `dispatch`, `token_dispatch` and `token_triggered_tags`, so a `null` `json_schema` inside them is rejected
- [Roadmap] DeepSeek V4.1 Optimization
- [Fix] Flush buffered text at stream end in MiMo, Step3, KimiK2, LFM2 detectors
- Support unified PD between matching DCP peers
- [Fix] Release buffered user text at stream end in InternLM, MiniCPM-5 and Hunyuan detectors
- [Fix] Flush buffered text at stream end in Pythonic, Inkling, Gemma-4 and Poolside V1 detectors
- [AMD] Add gfx1250 Gluon FAv3 diffusion backend
- [Fix] Flush buffered text at stream end in Llama-3.2 and dots detectors
- [Fix] Flush buffered text at stream end in Mistral, Hermes and GigaChat3 detectors
- [AMD] Enable GPTQ and AutoRound INT4 checkpoints
- Docs
- Python not yet supported