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
- [Feature] Add RVV kernels in sgl-kernel
- Add a flag for binding NIC to GPU for mooncake transfer engine in P2P RDMA weight sync
- Fix triton and wave attention backends for mamba-hybrid models
- [Fix] Recover plain content from empty Kimi tool sections
- [SPEC][4/N] feat: adaptive spec support ngram
- [Test-only] Add DeepSeek-V4 (compressed attention) model support
- [HiSparse] Support dynamic hisparse to reduce small-batch swap overhead
- fix(r-fork): allow weight-transfer endpoints with --enable-dp-attention
- Fix short standalone DeepSeek-VL2 image embeddings
- Cut repeated setup from DeepSeek-VL2 multi-image requests
- Docs
- Python not yet supported