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
- [ROCm][DSV4] Add FP4 LiteTopK indexer path
- [Spec] Fix EAGLE3 aux-layer capture for Qwen3.5
- perf(model): lossless final-layer prefill optimization for GLM models
- [Playground] Verified cell: h100 / flash-official / fp4 / high-throughput / single
- [HiCache] Feed existence beliefs only for the storage-written prefix
- [PD][MORI] Enable packed DCP1-to-DCP-N KV transfers
- [Bug] Chunked Prefill + Radix Insert race corrupts KV pages (QSA, Qwen3.8-Flash-Next)
- [MoE] Add FlashInfer SM120 W4A8 MegaMoE backend for DeepSeek-V4-Flash
- [Perf][DSA] Skip absorb-q concat when nope/rope already abut
- fix(hicache): fix MTP layer addressing under CP layer split
- Docs
- Python not yet supported