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
- scheduler: correct load metric
- [Deterministic] Support TP-Invariant Inference
- [VLM] Refactor ViT CUDA Graph key generation
- [TO BE EXTRACTED] Add Redis to ManualPolicy
- Support UVA Storage Framework
- [Feature] Carefully remove duplicated cotents in SGLang Docs and SGLang Cooklook
- [nit] Remove redundant server_args log in Engine.__init__
- [Perf] Add support for fused down GEMM + combine kernel (EP over NVLINK)
- [Feature] Add RVV kernels in sgl-kernel
- Add a flag for binding NIC to GPU for mooncake transfer engine in P2P RDMA weight sync
- Docs
- Python not yet supported