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] Qwen3-VL: chunk position embedding interpolation for large images
- [Bug] HiCache L3 prefetch hits are evicted before admission under L2 pressure
- [Feat] [MLU] ops: Add fused operator support
- [Test] linker: Update the Mooncake load-thread test stub
- [Bug] Quark utility import writes optional AITER cache before quantization
- [Fix] quark: Defer optional AITER quantizer imports
- [Perf] cp: Reuse interleave row copy for ragged gathers
- [Perf] diffusion: Route SANA-Video 2.0 RoPE through the fused fp64 interleaved RoPE kernel
- [Fix] Harden CPU bootstrap and bound capacity search
- [Fix] Preserve packed KV geometry on CPU
- Docs
- Python not yet supported