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

Sampler is failing with All input tensors need to be on the same GPU, but found some tensors to not be on a GPU: #56

Open
Morisgit148 opened this issue Jan 3, 2025 · 5 comments

Comments

@Morisgit148
Copy link

workflow
error
workflow2

ERROR=
All input tensors need to be on the same GPU, but found some tensors to not be on a GPU:
[(torch.Size([1, 4718592]), device(type='cpu')), (torch.Size([147456]), device(type='cpu')), (torch.Size([3072, 3072]), device(type='cpu'))]

ran from GPU.bat
Failing for every sampler i have BITS and bytes installed updated Compfui tried everyting but getting same error i m able to run forge with the bnbnf4v2 and version1 failing on COMFYUI

running on gpu RTX 3060 = 6gb vram and corei9 16GB Ram

@teherauto
Copy link

Yeah, same problem. RTX3070 8GB VRAM and 32GB i7 notebook.

@KLL535
Copy link

KLL535 commented Jan 8, 2025

same problem

@bluesky61
Copy link

Same error

@blitzk241
Copy link

same error

@Gmanskyi
Copy link

i got same trouble, 3080 10gb, pytorch version: 2.5.1+cu124, ComfyUI Version: v0.3.8, 49gb ram

KSampler
All input tensors need to be on the same GPU, but found some tensors to not be on a GPU:
[(torch.Size([4718592, 1]), device(type='cpu')), (torch.Size([1, 3072]), device(type='cuda', index=0)), (torch.Size([1, 3072]), device(type='cuda', index=0)), (torch.Size([147456]), device(type='cpu')), (torch.Size([16]), device(type='cpu'))]

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

7 participants
@bluesky61 @teherauto @Gmanskyi @KLL535 @Morisgit148 @blitzk241 and others