Enumerated shape

[metascroy]

Summary

This adds enumerated shape support for ExecuTorch's CoreML backend.

The CoreML backend supports dynamic shapes for the CPU/GPU. This enables enumerated shapes to support limit dynamism on the ANE.

These are done via compile specs:

enumerated_shapes = {"x": [[3, 5, 10], [4, 6, 10]], "y": [[3, 11], [5, 11]]}
...
compile_specs.append(
    CoreMLBackend.generate_enumerated_shapes_compile_spec(
        ep,
        enumerated_shapes,
    )
)
partitioner = CoreMLPartitioner(compile_specs=compile_specs, lower_full_graph=True)
delegated_program = executorch.exir.to_edge_transform_and_lower(
    ep,
    partitioner=[partitioner],
)

At runtime, one of the enumerated shapes must be supplied, or an error will occur.

Test plan

New E2E tests

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13613

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures

As of commit d562816 with merge base 3db27cd ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  At least one of the pre-conditions you specified did not hold
• pull / unittest-arm-backend-with-no-fvp (test_pytest_ops) / linux-job (gh)
  RuntimeError: Command docker exec -t e350b5f2174e017971cd46b6d8595ddf7238168fb37f59c2c09fd0395984141f /exec failed with exit code 1
• trunk / test-arm-backend (test_pytest_ops_ethosu_fvp) / linux-job (gh)
  RuntimeError: Command docker exec -t 28cb0c59a2a8625d32631e5e190768aca0bf68b78d1479d3f8f4f835008f5bb7 /exec failed with exit code 1
• trunk / test-llama-runner-mac (fp32, coreml) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80848324.

[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.

[cccclai]

LGTM

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80848324.

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80848324.