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

ToonCrafter Not Working with Pytorch 2.4 #111

Open
davidledo opened this issue Sep 15, 2024 · 1 comment
Open

ToonCrafter Not Working with Pytorch 2.4 #111

davidledo opened this issue Sep 15, 2024 · 1 comment

Comments

@davidledo
Copy link

Hello,

I had no problems working with ToonCrafter in the past, but somehow today I'm not able to run it. After about an hour of digging, I think it comes down to the version of Pytorch from one of the latest Comfy updates.

Is there a way to solve this? I tried downgrading Pytorch, but that breaks comfy.

Thanks!

Here's the error report details:

## Error Details
- **Node Type:** ToonCrafterInterpolation
- **Exception Type:** NotImplementedError
- **Exception Message:** No operator found for `memory_efficient_attention_forward` with inputs:
     query       : shape=(80, 2048, 1, 64) (torch.float16)
     key         : shape=(80, 2048, 1, 64) (torch.float16)
     value       : shape=(80, 2048, 1, 64) (torch.float16)
     attn_bias   : <class 'NoneType'>
     p           : 0.0
`decoderF` is not supported because:
    xFormers wasn't build with CUDA support
    attn_bias type is <class 'NoneType'>
    operator wasn't built - see `python -m xformers.info` for more info
`[email protected]` is not supported because:
    xFormers wasn't build with CUDA support
    operator wasn't built - see `python -m xformers.info` for more info
`cutlassF` is not supported because:
    xFormers wasn't build with CUDA support
    operator wasn't built - see `python -m xformers.info` for more info
`smallkF` is not supported because:
    max(query.shape[-1] != value.shape[-1]) > 32
    xFormers wasn't build with CUDA support
    dtype=torch.float16 (supported: {torch.float32})
    operator wasn't built - see `python -m xformers.info` for more info
    unsupported embed per head: 64
## Stack Trace ```
@farside-anim
Copy link

Yeah, I ran into the same issue this last week. I'm working on trying to figure it out and will let you know if I do.

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

2 participants