Pytorch1.5.0/win7 64bit/ Didn't find engine for operation quantized::conv2d_prepack NoQEngine

Pytorch 1.5.0+cu92
Windows7 64 bit
model.qconfig = torch.quantization.default_qconfig
torch.quantization.prepare(model, inplace=True)
torch.quantization.convert(model, inplace=True)

<---- Here
Exception has occurred: RuntimeError
Didn’t find engine for operation quantized::conv2d_prepack NoQEngine

Could you check if the USE_FBGEMM macro is turned on in your build environment? I believe it should be supported.

cc @dskhudia who might be able to add more info.

We use VS 14.11 to build binaries for CUDA 9.2, so there is no FBGEMM support. If you need FBGEMM, then please use the binaries with other CUDA versions instead.