support SageAttention

[a120092009]

Sage Attention provide low-bit quantization of attention. https://github.com/thu-ml/SageAttention

Seems like SageAttention supports plug-and-play way.. Will Diffusers plan to support sage attention by options?

import torch.nn.functional as F

+ from sageattention import sageattn
+ F.scaled_dot_product_attention = sageattn

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[a-r-r-o-w]

Marking as a duplicate of #11168