I would like to show you a little example how to boost speed of model training and inference with help of Intel oneAPI.
Just have a look on this standard Jupyter environment with code:
The main idea - with 2 lines of additional code:
from sklearnex import patch_sklearn
patch_sklearn()
you can boost training speed ~ x2 for this simple case.
All relevant documentation you can find
here
HINT:
After patch you have to import sklearn (
NOT BEFORE)
Try it
yourself and have a happy ML-ing...