Engine is the main force of the
It defines the logic of hardware communication and different deep learning techniques usage
like distributed or half-precision training:
Thanks to the
it’s straightforward to adapt your pipeline for different hardware accelerators.
For example, you could easily support:
Moreover, we are working on other hardware accelerators support like DeepSpeed, Horovod, or TPU. You could watch the progress of engine development under the Engine API section.
If you haven’t found the answer for your question, feel free to join our slack for the discussion.