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
- Fix rollback for partially applied source patches
- Normalize LoRA paths at request boundaries
- Fix MoE MORI Accuracy Issue
- [Fix] Stop deriving the gpt-oss sinks dtype from the configured attention backend
- [diffusion] MiniMax-H3 quality="high" runs on Turbo-LoRA-merged weights — the audit gate has no adapter field
- [Bug] HF3FS HiCache hits ZeroDivisionError with DeepSeek-V4 logical KV anchor
- [AMD] Perf dsv4 enable heterogeneous AITER FHMoE
- [Bug] Reasoning parsers: text before the opening think token is routed four different ways (chunk-dependent, and one-shot keeps the literal marker)
- [Spec] Stage EAGLE draft-extend graph inputs before the verify launch
- [Bug] Qwen3.8-27B-FP8 reasoning content does not parse correctly in rust sgl-model-gateway
- Docs
- Python not yet supported