Play around with QDQ Support

[pranav-prakash]

As mentioned in microsoft/onnxruntime#7033 ORT added support for converting QDQ internally into the quantized equivalent. Since this is done via graph transform, it should work for Systolic -- we would need to change the assigned EP though I think

As also mentioned with microsoft/onnxruntime#7144 this makes it easy to run quantize-aware-trained models. We can play around with this if we need more accuracy than post-training quantization can give us.

[pranav-prakash]

More info on QDQ is also seen in this presentation I found: https://gist.github.com/daquexian/4107a9c94038af3aa429b3a3371b332d

[pranav-prakash]

If this is done we also need to bump quantizer to take advantage of QAT export support: https://github.com/pranav-prakash/onnxruntime-riscv/blob/2021-04-02/systolic_runner/docs/quantizer.md#exporting-quantized-models