One calibrated quant entry per tap. axis = None is per-tensor;
axis = Some(d) is per-channel along axis d, in which case
scales and zero_points must each have length tap.shape.dim(d).
Insert Quantize → Dequantize pairs at every tap in record.
Returns a graph where each tagged node is followed by a
Quantize → Dequantize pair, and every consumer of the original
tap reads from the dequantized output instead.