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
- Add KV events from LMCache
- Fix bug when both enable piecewise cuda graph and mamba extra buffer
- docs(cookbook): Qwen3.6 config-driven deployment + measured speed benchmarks
- [AITER-Upgrade] PR readiness
- refactor(attn): converge metadata bodies into _compute_forward_metadata per backend
- [Apple Silicon] [MLX] Fuse MoE combine multiply-reduce into one Metal kernel
- [diffusion] Support LLaDA-Image BF16 generation and editing
- [AMD] GDN linear out-proj fusion
- [AMD] Enable unified-KV HiSparse on ROCm for DeepSeek-V4
- [KDA] Add zero-copy native prefill checkpoints and packed decode
- Docs
- Python not yet supported