You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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)
The text was updated successfully, but these errors were encountered:
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)
The text was updated successfully, but these errors were encountered: