Hello! I am trying to run a model on iOS using the metal backend - it works completely fine on iOS using the CPU backend, even if it is quantized; however using the metal backend does not work even if it is unquantized.
The error I am receiving is:
Could not run 'aten::as_strided' with arguments from the 'Metal' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'aten::as_strided' is only available for these backends: [CPU, QuantizedCPU, BackendSelect, Functionalize, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy].
I am using PyTorch Nightly. I assume that the error means that one of the operations is not supported on the Metal backend - is there any workaround for this?
Thanks!