Metadata-Version: 2.1
Name: comfyui-flex-attention
Version: 1.0.0
Summary: Flex Attention (torch.compile) node for ComfyUI. Uses PyTorch's built-in flex_attention with torch.compile — no extra dependencies, works on any GPU. Falls back to PyTorch SDPA when masks are present.
Home-page: https://github.com/sorryhyun/comfyui-flex-attention
Requires-Python: >=3.10
