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
- [qwen 3.8 next] Skip speculative KV allocation transfers when no pages are needed
- [qwen 3.8 next] Fuse simulated speculative acceptance tensor preparation
- [qwen 3.8 next] Fuse speculative relay payload stores and avoid single-request gathers
- [qwen 3.8 next] Fuse hybrid speculative state commits across state pools
- [qwen 3.8 next] Fuse exact greedy chain verification with argmax finalization
- [qwen 3.8 next] Fuse Mamba tracking index lookup and skip uniform-position transfers
- [qwen 3.8 next] Fuse NEXTN verify and draft graph input preparation
- [Fix] Voxtral: request token ids from apply_chat_template
- [Bugfix] Align Rust Qwen chat prompt preprocessing with Python
- Fix Responses API additional_tools input handling
- Docs
- Python not yet supported