Add support for quantized deconv #7640
Description
🚀 The feature, motivation and pitch
We already have support for deconv (or transposed conv) from #7514. However, we need to update XNNPACK quantizer which lives in PyTorch/PyTorch for this op, and update the paritioner config to lower this as a quantized operator.
Alternatives
None.
Additional context
No response
RFC (Optional)
No response
cc @mcr229