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
- [AMD] Add opt-in radix-select top-p pivot to the ROCm Triton renorm
- [AMD][DSv4] Emit the wo_a mxfp8 activation from the paged-decode epilogue
- Fix Baidu/Qianfan-OCR and stepfun-ai/GOT-OCR2_0
- [Fix] Reject malformed native generation inputs before dispatch
- [Metrics] Populate num_paused_reqs gauge during pause_generation
- [PDMux] DeepSeek-V4.1-Flash integration reference (split stack)
- [CPU] enable model hy3-fp8 on xeon
- [NPU] Fix prefill context parallel for generic (non-DSA) attention
- MSCCLPP EP
- Supports host RDMA communication protocol in PD disaggregation scenarios
- Docs
- Python not yet supported