[QST] Modifyinf a conv2d kernel and using it with python and pytorch

[IzanCatalan]

What is your question?
Hi, I aim to modify a convolution2d kernel to use it in Python with Pytorch later while performing the inference of a neural network model as Resnet50.

Basically, it is to change the base convolution kernel to add an extra parameter that modifies the weights.

I would like to know which is the easiest way to make this change, if on the kernel implementation itself in C++ and then also if I should use Cutlass with Python or Pycutlass. I am still determining precisely what is the difference between them and which one can help me more in my goal. Apparently, it seems that Pycutlass is deprecated; I don't know if this is confirmed.

Thanks

[github-actions]

This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.