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
- [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
- [Unified Cache] Support out-of-tree external linkers
- [sgl-router] Abort unfinished engine requests on cancellation
- [sgl-router] Fail fast on prefill errors and isolate PD transfer groups
- Refactor HiCache host pool assembly with declarations
- Docs
- Python not yet supported