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
- [PD] Vectorize disaggregation staging gather/scatter with validated alignment
- [Bug fix] gemma4_detector: handle string arguments whose opening delimiter is omitted
- w4afp8 read ignored_layers in from_config
- [MLX] Release finished requests' caches at every launch, not only on decode
- [Fix] Load pack-quantized fc weights for DFlash2 drafts (#39087)
- fix: derive compact ragged CUDA graph slots from request width
- [NPU] L2 cache offload overlap
- [Bug] Streaming top_logprobs reports the first token's alternatives for every token in a multi-token chunk
- Allocate packed weight receive buffers directly from metadata
- [BugFix][DSA] Respect tensor strides in the decode page-table transform
- Docs
- Python not yet supported