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
- [Doc] [NPU] qwen3.8-flash-next: Add Ascend A2 deployment tutorial
- Let DeprecatedChoiceToFlagAction accept the caller's SUPPRESS default
- [Fix] [NPU] mooncake: register device allocation spans
- [Fix] hicache: validate MLA rows before packing draft caches
- [Perf] scheduler: price host cache reloads in prefill LPM
- [Perf] [NPU] moe: tile local prefill expert activations
- [Feat] pd: add capacity-aware decode session placement
- [Perf] pd: overlap prefill rank publication and transfer retirement
- [Feat] [NPU] hicache: add exact-size ACL pinned host allocation
- [Fix] moe_topk_sum: fold rows past CUDA's 65535 gridDim.y into gridDim.z
- Docs
- Python not yet supported