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][Kimi-K3]: skip the routed_input copy when Aiter reads the front slice as-is
- docs: remove unreliable DeepWiki badge
- [AMD][Diffusion] Add a reliable gfx1151 attention path without AOTriton
- [RFC] Gluon MegaMoE: EP8 MXFP4 and EP16 FP8 Support
- [AMD] Compress QSA extend groups that cross an exact-chunk-fill prefix
- [NPU] Add opt-in CANN sparse attention for Qwen4-Exp QSA prefill
- [XPU] split Intel nightly into kernel-main and release (wheel) jobs
- [AMD][gfx1250] Enable fp8 wo_a bpreshuffle GEMM for MI455
- [NPU] Support compact indexer KV cache for DSA models in disaggregated Prefill/Decode
- Fuse FP8 row-padding zero fills into group quantization
- Docs
- Python not yet supported