Add regression tests for previously-failing CoreML lowerings

[john-rocky]

Summary

Six bugs filed against the CoreML partitioner / backend in mid-2025 no
longer reproduce on the current toolchain (executorch main + coremltools 9.0):

• CoreML crashes when running convolution #11688 — Conv1d(stride=8, dilation=2, groups=2) segfault
• CoreML int32 mm with fixed arg fails to load at runtime #11691 — int32 matmul with a constant weight failed to load
• CoreML BatchNorm3d crashes process #11701 — BatchNorm3d crashed during compilation
• CoreML InstanceNorm3d fails to load #11702 — InstanceNorm3d failed at compile with invalid rank 5
• CoreML ReflectionPad3d fails to load at runtime #11708 — ReflectionPad3d failed to load with the >2-spatial-dim pad error
• CoreML ReplicationPad3d fails to load at runtime #11709 — ReplicationPad3d same as CoreML ReflectionPad3d fails to load at runtime #11708

I verified each repro on macOS 15 / Python 3.10 / coremltools 9.0 and they
now lower cleanly. This PR adds them to test_coreml_partitioner.py so
the wins are pinned in CI, and any future change that regresses one of
them surfaces immediately.

Test plan

$ python -m unittest -v executorch.backends.apple.coreml.test.test_coreml_partitioner.TestCoreMLPartitioner.test_previously_failing_ops_lower_successfully
Ran 1 test in 2.677s

OK

The test is a single method with one self.subTest(name=...) per issue so a
re-regression of any one case is reported individually. I'm happy to follow
up with separate "closes" comments / closes on the issues themselves once
this lands.

Authored with Claude.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19248

• 📄 Preview Python docs built from this PR

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

⚠️ 12 Awaiting Approval

As of commit 0f27740 with merge base 94d2881 ():

AWAITING APPROVAL - The following workflows need approval before CI can run:

• Apple (gh)
• Build documentation (gh)
• Build Presets (gh)
• Cadence Build & Test (gh)
• Lint (gh)
• periodic (gh)
• pull (gh)
• Test ARM Backend (gh)
• Test CoreML Backend (gh)
• Test QNN Backend (gh)
• Test Vulkan Backend (gh)
• Test XNNPACK Backend (gh)

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

[meta-cla]

Hi @john-rocky!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[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.