[Feature Request] Offline optimization for CoreML

[Rikyf3]

Describe the feature request

When you load a model using CoreMLExecutionProvider it takes a very long time, even minutes for big models. If you look at the logging of onnxruntime you can see that it is saving .mlpackage files in a temp folder. Can the possibility of loading saved compiled model, with offline optimization, like as in other EPs be added to CoreML EP?

Describe scenario use case

To speedup model loading when using CoreML provider.