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
- NPU: add sleep-mode comm cleanup support
- [XPU] Enable RL feature on Intel XPU
- [Kimi K3] Tool-call request conformance: grammar relaxations, dynamic tools, forced-call semantics
- [Kimi K3] Honor the Moonshot thinking request object and map effort onto K3 tiers
- [Kimi K3] Streaming wire conformance for the Kimi K3 chat contract (KVV stream-spec)
- [Feature] Kimi-K3 Kimi-Vendor-Verifier (KVV) conformance:
- fix(npu): route small-page prefill through FIA
- [AMD][Unified Cache] Split UMBP loads across TP ranks
- [AMD] Fuse Qwen3.8 GDN prefill prologue and MXFP4 output epilogue
- [Kimi-K3] Add EPLB integration
- Docs
- Python not yet supported