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
- [HiCache] Intersect restorable prefixes across pools and ranks
- [HiCache] Treat file read errors as cache misses
- [Bug] DP scheduler rank can permanently stop processing requests after a near-KV-capacity request is cancelled
- [Bugfix] Prevent DP scheduler hang near KV capacity
- [Feature] Interleaved Prefill Pipeline Parallelism for DeepSeek-V4.1: PP4 x CP2 with Two Virtual Stages per Rank
- [MLX] Keep FutureMap relay buffers on CPU under the MLX backend
- [Bugfix] Accept empty PP input in DSpark non-overlap dispatch
- [Bugfix] Fix Gemma auxiliary hidden-state captures
- [Bugfix] Fix EAGLE sliding-window verification in FlashInfer and Triton
- Fix power-of-two activation scales for DSV4 fp8_einsum
- Docs
- Python not yet supported