Recently, deep learning projects have been getting larger, and sometimes loading models has become a bottleneck. I download the .mlpackage format CoreML from the internet and need to use compileModelAtURL to convert the .mlpackage into an .mlmodelc, then call modelWithContentsOfURL to convert the .mlmodelc into a handle. Generally, generating a handle with modelWithContentsOfURL is very slow. I noticed from WWDC 2023 that it is possible to cache the compiled results (see https://developer.apple.com/videos/play/wwdc2023/10049/?time=677, which states "This compilation includes further optimizations for the specific compute device and outputs an artifact that the compute device can run. Once complete, Core ML caches these artifacts to be used for subsequent model loads."). However, it seems that I couldn't find how to cache in the documentation.
Hello @coreml_student,
The model specialization and caching mentioned in that video happens automatically, you don't need to do anything additional :)
You can check if your model is being loaded from the cache using instruments, as mentioned at this part of the same video: https://developer.apple.com/videos/play/wwdc2023/10049/?time=725
Best regards,
Greg
