Using a new macports receipt to build onnxruntime there’s basic coreML support for both builds. macOS 14.4 is required to enable further optimizations eg using more modern MLProgram engine.
you might run it with an in-memory library via terminal: /Volumes/darktable/darktable.app/Contents/MacOS/darktable --library :memory:
or use a separate config directory: /Volumes/darktable/darktable.app/Contents/MacOS/darktable --configdir ~/.config/darktable_test
also keep in mind that if you don’t disable writing sidecar files these can be messed up
both packages are unsigned, you might need to allow execution via terminal: " xattr -c <path/to/application.app> "
Using a new macports receipt to build onnxruntime there’s basic coreML support for both builds. macOS 14.4 is required to enable further optimizations eg using more modern MLProgram engine.
you might run it with an in-memory library via terminal: /Volumes/darktable/darktable.app/Contents/MacOS/darktable --library :memory:
or use a separate config directory: /Volumes/darktable/darktable.app/Contents/MacOS/darktable --configdir ~/.config/darktable_test
also keep in mind that if you don’t disable writing sidecar files these can be messed up
both packages are unsigned, you might need to allow execution via terminal: " xattr -c <path/to/application.app> "