A Unified and Flexible Inference Engine with Cache Acceleration, Parallelism and Quantization for 🤗Diffusers.
          flux          wan          longcat          kandinsky          diffusers          nunchaku          context-parallelism          qwen-image          qwen-image-lightning          huanyuan-image          longcat-video      
    - 
            Updated
            
Nov 4, 2025  - Python