Re:Deploying Transformers on the Apple Neural Engine
by hprotagonist on Wednesday June 08, 2022 @11:00AM
(#31668336)
which together are about 5 separate abstraction layers that don’t agree with each other. (tf 1,2, keras, torch, torch functional, …)
so we add onnx and trt on top! that’ll help, right?
Eh ... lots of people use Tensorflow or Torch.