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] Skip quantized MoE compatibility check for dense models whose configs inherit MoE fields
- [Bug] /v1/responses and /v1/chat/completions return 400 when a function tool has "strict": null
- Fix inverted assertion message for enable_mixed_chunk with speculative decoding
- fix(openai): accept nullable strict in function tools
- [Bug] MLA KV writers can overwrite reserved padding slot 0
- [rust-server] fix rust dp listener port
- fix(dflash): reject unsupported PD disaggregation
- Main CI test
- [Bug] --config rejects canonical mamba-radix-cache-strategy due to DeprecatedAliasStoreAction
- [NPU][Kimi-K3] Honor --moe-dense-tp-size 1 for dense MLP
- Docs
- Python not yet supported