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]fix(dspark): preserve parity in folded NPU paths
- [Fix][DSA] Fail loudly when trtllm-gen query rows exceed the CUDA gridDim.z limit instead of silently skipping attention
- [OpenAI] Preserve images in Responses tool outputs
- [AMD] Fix ROCm FP8 DP gather quantization
- [Observability] Trace DP controller delivery stalls
- fix(sgl-kernel): preload CUDA runtime before loading common ops
- Support compressed-tensors NVFP4 Marlin with BF16 and DSpark
- [Bug] HiCache host-pool memory check (psutil.virtual_memory().available) does not account for reserved HugePages, causing false "Not enough host memory" failures
- AMD Development Roadmap (2026 Q3)
- fix: handle empty e2e latency metrics
- Docs
- Python not yet supported