Lower GPU memory requirements at ONNX export (#1115)
* verbose
* squash
* fixes
* add comment
* slight refactor
* define get_inputs
* fix tests
* fix tests bis
* Update optimum/exporters/onnx/convert.py
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
---------
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
