Fix IndexError in RemovePermutesAroundElementwiseOps for rank-mismatched views (#19713)

[mcremon-meta]

Summary:

Fix an IndexError crash in the RemovePermutesAroundElementwiseOps
compiler pass that occurs when a squeeze/unsqueeze view_copy node is
included in a subgraph via upstream traversal with a permutation whose
rank does not match the view input tensor rank.

The bug manifests as IndexError: tuple index out of range in
update_view_copy at the line:

unpermuted_in = [in_shape[inverse_permute[i]] for i in range(len(in_shape))]

because inverse_permute contains indices from a rank-N permutation
but in_shape has fewer than N dimensions.

The fix adds a validation guard at the top of permute_subgraph() that
checks all view_copy nodes for rank consistency between their
node_start_permute and their input tensor shape. If a mismatch is
found, the entire subgraph optimisation is skipped, preserving graph
correctness. The return type of permute_subgraph is changed from
None to bool so the caller only marks the graph as modified when the
subgraph was actually transformed.

Also adds a regression test that constructs the exact graph pattern
(upstream unsqueeze view_copy with a 2D constant feeding into a 3D
permuted add) that triggered the crash.

Reviewed By: ethansfng

Differential Revision: D105787161

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19713

• 📄 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:

• Run pull request jobs on OSDC runners in shadow mode

❌ You can merge normally! (2 Unrelated Failures), 1 Unclassified Failure

As of commit 8b56e75 with merge base da01860 ():

UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:

• Check Labels / Check labels (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  RuntimeError: GraphQL query

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)
• trunk / test-multimodal-macos (gemma3-4b) / macos-job (gh) (detected as infra flaky with no log or failing log classifier)

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

[meta-codesync]

@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D105787161.

[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.