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] qwen3_5: enable GDN fused decode projection+Conv1D on HIP
- disagg(PD): make multimodal token-count divergence diagnosable at DSA state transfer failure
- [dLLM] Size decode graph buffers by the separate-context request cap
- [AMD] Enable aiter attention backend for DSR1 on gfx1250.
- [ROCm] qwen3_5: use strided GDN prefill projection views on HIP
- [MoE] Add an opt-in W4A4 (MXFP4 activation) path to the DeepGEMM runner
- [NPU] add e2e test for some parameters on NPU
- [diffusion] perf: row-shard MiniMax-H3's TP=2 residual behind DeepGEMM
- [KV Cache] Amortize L1 eviction under sustained pressure
- [PD] Reload NIXL peer metadata after the peer is invalidated
- Docs
- Python not yet supported