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
- [AMD] AgentX draft slot 3
- [AMD] AgentX draft slot 4
- [AMD] AgentX draft slot 5
- [AMD] AgentX draft slot 6
- [SMG] Preserve Responses payloads when forwarding to HTTP workers
- [Perf] flashinfer: Autotune kernels at prefill sizes by default
- fix(moe): reject K tiles that cross block-scale boundaries
- perf(spec): broadcast additive penalties over verify tokens
- [Spec] Shard the Qwen3.5 top-1 MTP draft head across node-local TP4 groups (opt-in)
- [Bug] Model gateway drops x-override-priority and the chat body priority, so priority cannot be set behind it
- Docs
- Python not yet supported