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] A cancelled grammar-constrained overlap request can still emit visible text before abort
- [Doc]The invalid links in the document
- [router] Add bucket range config parsing, validation, and selection h…
- [Fix] Give multimodal draft-extend one mRoPE position per extended token
- [Bug] Aborted LoRA requests retain a LoRARegistry reference
- [bugfix] fix prefill finish_abort but decode alse running cause error result bug
- [Bug] Streaming response truncates content when both content and tool_calls are present (SGLang 0.5.17)
- Detect scheduler death in the DP controller instead of blocking on recv
- [PD] Fix NIXL P/D serving stall after prefill replacement
- Support online NVFP4 for dense linear layers
- Docs
- Python not yet supported