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
- Strip --speculative-draft-model-path when switching Playground speculative presets
- [DeepSeek-V4] Support Batched and Round-Robin CP Prefill in the Non-Paged Indexer
- [ROCm] Support power-of-2 scales in the row-major per-token-group quantizer
- [gdn] fuse verify commit indices into one kernel
- [DSpark] Add MiniMax-M3 DSpark support
- fix(hicache): support L3 storage for layer-sharded MLA
- fix(connector): Honor Redis file selection
- [RFC] PD disaggregation: single protocol layer, per-backend transport
- [Bugfix] Apply additive penalties during DFlash verify
- [Multimodal] Broadcast large CPU features outside pickle
- Docs
- Python not yet supported