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
- [Draft Feature] Add a shared KV compression framework for P/D transfer and HiCache L2
- [bench] Fix warm-cache benchmark under-counting streaming output tokens
- [NPU] fix precision bug when enable mixedchunk and breakable prefill graph for qwen3
- [Bug] MooncakeHostTensorAllocator wraps a null pointer from the host allocator instead of failing at the allocation site
- [HiCache] Fail fast on a null pointer from the Mooncake host allocator
- [DSV4.1][DSpark] Enable dynamic verify on PD decode
- [Fix] Check pynccl availability before entering change_state in all_gatherv/reduce_scatterv
- [Bugfix] Fall back from batch D2H copies when host memory is not device-visible
- [HiCache] Add watermark-triggered asynchronous write-back
- [NPU] Add FP8 FIA attention backend
- Docs
- Python not yet supported