Does Python's datatable package support out-of-memory datasets?

Question

datatable is a relatively fresh high performance DataFrame/data.table alternative for Python. The datatable documentation states:

It focuses on: big data support, high performance, both in-memory and out-of-memory datasets, and multi-threaded algorithms.

Still, haven't found operations related to caching or keeping a part of the data out-of-memory. In what sense does it support out-of-memory datasets?

Recto

If you have big data , I recommend dask – Blowsy

@WeNYoBen, my data first the memory of our servers for now, just curious what different frameworks can offer... I'm looking at dask and modin as well, thanks! – Recto