Hello everyone, I hope you are all well. I would like to quickly clarify a doubt about mlforecast. During the transfer learning process

model_lgbm.predict(h=15, new_df=new_skus_df)

Is it possible to parallelize this process? Because there are more than 300k distinct series Thanks in advance!

Hey. It will use the

num_threads

argument that you set in the MLForecast constructor for that. Is it taking too long?

thank you José! I didn’t know about this mechanism, I’m going to spin up a larger machine here on Sagemaker and add more threads to test.

Also, are you using the built-in lag transforms or numba ones? I saw there are some cases where the GIL blocks the numba ones (even though it's supposed to bypass it)