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
- [CPU] Add FP8 quantization support for compressed-tensors paths
- [CPU] Add INT8 quantization support for per-token and compressed-tensors W8A8 paths
- [CPU] Add GGUF Q4/Q8 and AMX quantization support
- Optional per-request settlement rail (HTTP 402) for metered self-hosted serving
- [PD][DSA] Register the NextN draft's DSA index cache for hybrid linear-attention pools
- [Spec][PP] Allow PP + EAGLE/NEXTN prefill for Glm5Next
- [Unified Cache] Support hybrid SWA + Mamba models in the Mooncake direct linker
- [AMD] Use read-only safetensors mapping on integrated GPUs
- [fix] kt: read num_hidden_layers from text_config for multimodal checkpoints
- Keep sigmoid(beta) in fp32 in GDN/KDA decode kernels
- Docs
- Python not yet supported