PyTorch was long associated with research and the ML community, TensorFlow with the engineering of wearables and industrial automation. And moving a PyTorch model onto embedded hardware (anything beyond a Linux-based board) ultimately meant deploying through LiteRT or TensorFlow Lite for Microcontrollers.
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/from-pytorch-to-the-edge-getting-started-with-executorch-and-edge-impulse