Rescales the output corresponding to AQT style quantized matmul's weight. Uses the same scale used by `ToAqtWeight` and apply its inverse to rescale. w_name must have been previously created via TrackQWeight. Args: w_name: Previously created w_name QWeight to quantize weight.
(self, w_name, out, merge_feature_axes=False)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected