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
- [Perf] glm: Overlap KDA CP input gathering with projection
- [Feat] [NPU] sampling: Add DSpark Triton operators
- [Feat] [AMD] mori: Overlap shared experts with MORI EPv2 AsyncLL dispatch under SBO
- serving_chat: repair a terminal turn that only produced thinking
- [Fix] [Apple] mlx: Reject LoRA at startup
- [Fix] [Apple] mlx: Return an error for online weight updates
- [Perf] [AMD] distributed: Use AITER FlyDSL INT4 QuickReduce on gfx950
- [Fix] [NPU] tests: Serve sgl_eval MMLU data from a prefetched archive
- [Fix] scheduler: Reserve member rows of beam leaders admitted in the same prefill
- [Refactor] diffusion: normalize diffusers output layout in one place
- Docs
- Python not yet supported