[Core ML] Update Partitioner Test as Torch.Any Supported

[YifanShenSZ]

Motivation

In #4772, the partitioner test case was updated to have graph breaks, because pytorch/pytorch#131863 introduced safe softmax which involves torch.any op that was not supported in Core ML

Solution

In coremltools 8.1 release, torch.any support has been included, so

1. We upgrade executorch pinned coremltools to 8.1
2. We will no longer have graph breaks in the partitioner test case

Other Fixes

#5157 and #6201 are also resolved in coremltools 8.1

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6361

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• [DomainsOnly] Jobs fail with GLIBC version not found

❌ 4 New Failures

As of commit 6ea4092 with merge base 6ac19cc ():

NEW FAILURES - The following jobs have failed:

• Apple / build-benchmark-app / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• Apple / build-demo-ios / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• Apple / upload-frameworks-ios (gh)
  ##[error]Credentials could not be loaded, please check your action inputs: Could not load credentials from any providers
• Check Labels / Check labels (gh)
  RuntimeError: Error checking labels: PR does not have required labels

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

[github-actions]

This PR needs a release notes: label

If your changes are user facing and intended to be a part of release notes, please use a label starting with release notes:.

If not, please add the topic: not user facing label.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "topic: not user facing"

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

[YifanShenSZ]

@cccclai @shoumikhin

[cccclai]

Thanks!

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[YifanShenSZ]

Any legit CI error I should address?

[cccclai]

Any legit CI error I should address?

I think our CI is failing internally but it doesn't show up externally...need to get that fixed than land this diff. cc: @kirklandsign

[kirklandsign]

but it doesn't show up externally

No good workaround for this...

[cccclai]

@YifanShenSZ this test seems failing

executorch/backends/apple/coreml/test/test_coreml_partitioner.py

Line 59 in 6ac19cc

def test_vit_skip_conv(self):

[YifanShenSZ]

@YifanShenSZ this test seems failing

executorch/backends/apple/coreml/test/test_coreml_partitioner.py

Line 59 in 6ac19cc

def test_vit_skip_conv(self):

Passed on my local. What's the error you saw?

Just rebased, let's try again

[cccclai]

Ah acutally I may know why - the internal test probably runs with the old coreml package

[YifanShenSZ]

Ah acutally I may know why - the internal test probably runs with the old coreml package

Hmmm, how come? This PR also updates the pinned coremltools to 8.1, so if CI builds executorch & delegate from source then it should be using the latest?

[cccclai]

Ah acutally I may know why - the internal test probably runs with the old coreml package

Hmmm, how come? This PR also updates the pinned coremltools to 8.1, so if CI builds executorch & delegate from source then it should be using the latest?

Internally we pointed to a lower version..@shoumikhin helped importing the latest coremltools, we should be able to fix it then. So no action on your side, and wait for us :)

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[cccclai]

hmm it fails to import

    The Pull Request could not be imported cleanly from GitHub. This usually happens for one of two reasons:
    1. The Pull Request is out of date, if you rebase the PR on the latest commit on the GitHub branch and find merge conflicts this is probably the reason
    2. ShipIt is broken for this repo, check bunnylol `oss org/repo`, click on the ShipIt tab, and see if there are any alerts. Fix those and retry the import.

Can you rebase?

[shoumikhin]

I've already landed this change via the internal coremltools version bump since it failed tests otherwise.