Wow, this seems to be a new way to convert PyTorch models to a format that runs across CPU, GPU & Apple's Neural Engine (ANE). [0]

Does this completely replace the previous API, CoreML? [1]

  [0]: https://apple.github.io/coreai-optimization/
  [1]: https://developer.apple.com/documentation/coreml/

Yes. From the CoreAI docs:

"If your app uses model types other than neural networks, such as decision trees or tabular feature engineering, see Core ML."

This is just a bit exciting, although I wonder how the performance of this will stack up next to the stuff we already do with, e.g., a metal-optimised model which we then load into llama-cpp or whatever. (unsloth is a good example of doing this for you "batteries included").

seems they planning to replace it but overall now I'm really confused about this and mlx and coremltools. They should do better work explaining the benefits (and cons) of it and any feature parity between coreai, coreml and mlx.

Requires OS 27+, so CoreML is still useful for backwards compatibility.