hmzjwhmzjw

## detail | 详细描述 | 詳細な説明 class Model(nn.Module): def __init__(self, pnnx_bin="pretrained/weights.bin"): super(Model, self).__init__() ... archive = zipfile.ZipFile(pnnx_bin, 'r') ...

_flash_attention_3 in dispatch_attention_fn is not compatible with the latest flash-atten interface.

6

### Describe the bug [FA3] Don't return lse: https://github.com/Dao-AILab/flash-attention/commit/ed209409acedbb2379f870bbd03abce31a7a51b7 but in the current diffuser version, it is not updated. https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_dispatch.py#L608 when use fa3 backend, diffuser will raise error. ### Reproduction...