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
- [Bug] DP scheduler rank can permanently stop processing requests after a near-KV-capacity request is cancelled
- [Bugfix] Prevent DP scheduler hang near KV capacity
- [MiniMax-M3] Add native SM90 Q8K8 sparse prefill Step 1
- [Bug] [NPU][MoE] AscendTPDispatcher downcasts FP32 routing weights to the hidden-state dtype
- fix(dsv4): support R3 capture and MXFP4 online updates
- [Bug] Kimi-K3 cookbook image (sglang 0.5.16) hangs in the first TP16 decode step on 4 nodes x 4 GB200
- [AMD] [Fix] Handle unaligned QSA extend prefixes from chunk-cache tails
- [dLLM] Preserve prompt tails and literal mask tokens across prefix reuse
- Greedy decoding is not reproducible across server restarts when FlashInfer autotune is enabled (DFLASH speculative decoding)
- [AMD] Add opt-in AITER ASM FP4 GEMM for Quark dense linear
- Docs
- Python not yet supported