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
- [FEAT][SpecDecode] Add DP attention support for DFLASH speculative decoding
- fix: warn about non-obvious chunked prefill budget behavior
- [Apple Silicon][MPS] Cap memory reporting to Metal's recommended working set
- [BCG][1/N] Route RMSNorm to fp32 forward_native under breakable prefill
- [refactor] Rename chunked_req_to_exclude to reqs_to_exclude
- Reduce top-level sglang import overhead
- [KDA] Support extra_buffer mamba radix cache for Kimi Linear
- feat: reject empty/whitespace-only assistant content in chat validation
- [Tracking] DSpark in SGLang: roadmap
- [NPU] eagle3 support modelslim quarot
- Docs
- Python not yet supported