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
- Fix #28808: Refactor TRTLLMHAAttnBackend inheritance structure
- [Feature] Support opt-in dp_rank-targeted health probes on /health and /health_generate
- Fix three logger calls that drop their record and print a logging error
- [ROCm] Add the AITER sparse-MLA kernel for DSA decode as option
- [diffusion] feat: add --encode-only serving mode returning encoder outputs via POST /encode
- fix(fa4): isolate sheared-bias workspaces by CUDA stream
- fix(attention): honor selected FlashAttention implementation
- Fix/k3 router tool choice default
- perf: compact sparse logit bias storage
- [ROCm] Use the AITER sparse-MLA kernel for DSA prefill and decode
- Docs
- Python not yet supported