Metal backend: Materialize non-packed tensor views in reinterpret_tensor

[manuelcandales]

AOTI generates reinterpret_tensor views with non-packed strides (e.g. chunk/split for RoPE rotation) that have holes in memory. ExecuTorch's make_tensor_ptr requires densely packed layouts.

When aoti_torch__reinterpret_tensor encounters non-packed strides, allocate a new contiguous Metal buffer and copy elements using strided access from the source.

Authored with Claude.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19033

• 📄 Preview Python docs built from this PR

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

❌ 1 Cancelled Job, 2 Unrelated Failures

As of commit cf71b8e with merge base 1d37abd ():

CANCELLED JOB - The following job was cancelled. Please retry:

• pull / unittest-buck / macos / macos-job (gh)
  ##[error]The operation was canceled.

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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.

[Copilot]

Pull request overview

This PR updates the Metal AOTI runtime shim to handle reinterpret_tensor views that have non-packed (holey) strides by materializing them into a newly allocated contiguous Metal buffer, aligning with ExecuTorch tensor construction requirements.

Changes:

• Added is_packed_strides() to detect when a strided view has “holes” (storage extent > numel).
• Added materialize_packed() to allocate a new Metal buffer and copy elements from the strided source view into a packed layout.
• Updated aoti_torch__reinterpret_tensor to materialize non-packed views, compute contiguous strides for the new buffer, and update ownership/refcount bookkeeping accordingly.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[metascroy]

Stamping, but maybe consider adopting SlimTensor to address this