CoreML partitioner improvements

[metascroy]

This creates several improvements for the CoreML partitioner:

• We now log when nodes are skipped for partitioning and the reason they are skipped.
• We add new partitioner option lower_full_graph that raises Exception if the model cannot be fully delegated. In future, when this option is enabled we plan to support additional CoreML features like enumerated shapes.
• We add take_over_constant_data option to tell CoreML delegate to not consume weight data.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12532

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 3 New Failures

As of commit 1b7b121 with merge base 6c51181 ():

NEW FAILURES - The following jobs have failed:

• pull / test-eval_llama-mmlu-linux / linux-job (gh)
  RuntimeError: Command docker exec -t e27120d46c6b031150a2d4618ded0f91deeb842eb94ebe8f93a280c74eee3303 /exec failed with exit code 1
• pull / unittest / linux / linux-job (gh)
  backends/xnnpack/test/ops/test_to_copy.py::TestChannelsLastTaggedReshapePass::test_quantized_to_copy
• pull / unittest-editable / linux / linux-job (gh)
  backends/xnnpack/test/ops/test_to_copy.py::TestChannelsLastTaggedReshapePass::test_quantized_to_copy

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[metascroy]

@JacobSzwejbka this adds take_over_constant_data to partitioner. If you don't want CoreML to consume the weights, you can set it to False.

[YifanShenSZ]

Great! 🚀 These were the pain points we've been having during development, nice to see them enhanced!