Fix the NaN bug

Previous version of the PTQ implementation could result in a model producing NaN values. This was due to a poor memory initialization obtained by doing a multiplication by zero. Thus, rescaleTensor(tensor, 0) is now replaced by fillTensor(tensor, 0) which solves the problem.

added 1 commit

• fe97cdf9 - bugfix + support of MSE cliping

Compare with previous version

added 1 commit

• c73febab - adaptative nb of cliping bins

Compare with previous version

added 1 commit

• a53f1117 - remove old code

Compare with previous version

added 1 commit

• 985035d8 - remove extra verbose

Compare with previous version

merged manually