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
- [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
- [diffusion][AMD] FlyDSL norm: pick the wave count per hidden size
- [diffusion][AMD] kernels: Fix fused QK-norm JIT kernels on ROCm
- [diffusion] USP: accept strided row views in the packed QKV all-to-all
- Fix compressed-tensors capability error formatting
- Implemented MXFP8 quant lightning indexer for DSA
- [Perf] Add model-level checkpoint page-cache release
- Docs
- Python not yet supported