About Hardware-Accelerated Machine Learning
M4 macmini installed immich via docker
Supported Backends
ARM NN (Mali)
CUDA (NVIDIA GPUs with compute capability 5.2 or higher)
ROCm (AMD GPUs)
OpenVINO (Intel GPUs such as Iris Xe and Arc)
RKNN (Rockchip)
Which of the above do I need to choose?