Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

"No operator found for memory_efficient_attention_forward with inputs" issue on Mac Pro M1 #376

Open
LinearFalcon opened this issue Jul 6, 2024 · 0 comments

Comments

@LinearFalcon
Copy link

Hi folks, run out of all my hacks so wanna to post here to see if anyone know how to run the latest sv3d_u model on Mac Pro M1 with device set to cpu?
I kept running into this issue even if I have already make sure the input PNG file is 576x576:

NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
     query       : shape=(1, 5184, 1, 512) (torch.float16)
     key         : shape=(1, 5184, 1, 512) (torch.float16)
     value       : shape=(1, 5184, 1, 512) (torch.float16)
     attn_bias   : <class 'NoneType'>
     p           : 0.0
`ck_decoderF` is not supported because:
    max(query.shape[-1] != value.shape[-1]) > 256
    device=cpu (supported: {'cuda'})
    operator wasn't built - see `python -m xformers.info` for more info
`ckF` is not supported because:
    max(query.shape[-1] != value.shape[-1]) > 256
    device=cpu (supported: {'cuda'})
    operator wasn't built - see `python -m xformers.info` for more info
@LinearFalcon LinearFalcon changed the title No operator found for memory_efficient_attention_forward with inputs issue on Mac Pro M1 "No operator found for memory_efficient_attention_forward with inputs" issue on Mac Pro M1 Jul 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant