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
- [NPU] Support dsv4 dspark on ascend 950
- [feat]: enhance fused MOE kernel with TMA support
- feat(EvictionStrategy): Add a new adaptive mixed cache eviction strategy to improving cache hit rate
- [Feature] Detailed Break down of time spend on Launching SGLang Diffusion
- [AMD] Enable FP8 KV cache for tilelang NSA backend
- Fix KTransformers MoE compatibility regressions in the current SGLang
- [Fix] Enable precise embedding interpolation by default for Qwen3-VL
- [Feature] Free-Threaded Python (3.14t / nogil) Support for SGLang
- Add test cases for NPU runtime_options feature
- AMD Development Roadmap (2026 Q2)
- Docs
- Python not yet supported