[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.

🪟 为 Windows AI 开发者提供预编译 wheel 文件的集中仓库 | 自动抓取并整理 PyTorch、Flash Attention、xformers、SageAttention 等常用库的最新版本 | 免编译，开箱即用 | 特别适合 ComfyUI 和 Stable Diffusion 用户

An all-in-one docker image that runs the latest ComfyUI with SageAttention.