Engine

Engine is the main force of the Runner. It defines the logic of hardware communication and different deep learning techniques usage like distributed or half-precision training:

Thanks to the Engine design, it’s straightforward to adapt your pipeline for different hardware accelerators. For example, you could easily support:

• PyTorch distributed setup.

• AMP distributed setup.

• DeepSpeed distributed setup.

• TPU distributed setup.

If you haven’t found the answer for your question, feel free to join our slack for the discussion.