[/usr/local/lib/python3.10/dist-packages/torch/random.py](https://localhost:8080/#) in manual_seed(seed) 40 torch.cuda.manual_seed_all(seed) 41 ---> 42 return default_generator.manual_seed(seed) 43 44 ModuleNotFoundError: No module named 'torch.mps' --- NOTE: If your import is f...
For your fix of non-Apple platform, I'm wondering what would happen when actually running on Apple device? I don't have an Apple device (with MPS) to test, I would like to propose the following: if torch.cuda.is_available(): torch.cuda.empty_cache() elif torch.backends.mps.is_avail...
'torchvision::nms' is only available for these backends: [CPU, QuantizedCPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, ...
File"/Users/xxxxxxxxxxxx/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/_refs/__init__.py", line 4254,inempty_likereturntorch.empty_strided( TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.Stab...
[/usr/local/lib/python3.10/dist-packages/torch/random.py](https://localhost:8080/#) in manual_seed(seed) 40 torch.cuda.manual_seed_all(seed) 41 ---> 42 return default_generator.manual_seed(seed) 43 44 ModuleNotFoundError: No module named 'torch.mps' --- NOTE: If your import is f...