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

多gpu支持 #56

Open
WuXunjin opened this issue Jan 9, 2025 · 0 comments
Open

多gpu支持 #56

WuXunjin opened this issue Jan 9, 2025 · 0 comments

Comments

@WuXunjin
Copy link

WuXunjin commented Jan 9, 2025

请问如何支持多GPU?单卡3090只能用lite模型save_memory,尝试修改app.py

parser.add_argument("--t2i_device", default="cuda:0", type=str)
parser.add_argument("--i2v_device", default="cuda:1", type=str)
parser.add_argument("--v2m_device", default="cuda:2", type=str)
parser.add_argument("--render_device", default="cuda:3", type=str)

报错

File "/home/admin/.conda/envs/hunyuan/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 125, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:2 and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)

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