Quantization Error During Concat -- RuntimeError: Didn't find kernel to dispatch to for operator 'aten::_cat'

There are a couple of options depending on what you want:

If you want quantized integer data, use int_repr (https://github.com/pytorch/pytorch/wiki/Introducing-Quantized-Tensor)

If you want float data, dequantize and use your existing way of converting it to numpy.