Hi, now that ARM64 has become a standard for both consumer and enterprise machines, there's now a lot of hardware with nvidia GPUs that are ARM64 based (jetson, AGX, DGX, ...), it'd be super valuable to support this architecture in your docker image builds for CUDA runtime 🙂
I see that there is no ARM64 image build for immich-machine-learning:
$ skopeo inspect docker://ghcr.io/immich-app/immich-machine-learning:v2.2.0-cuda
FATA[0001] Error parsing manifest for image: choosing image instance: no image found in image index for architecture arm64, variant "v8", OS linux
Thanks in advance for the help, you rock 🚀 !
.