[ExecuTorch][WebGPU] permute_copy op test suite (cases.py op-test framework)

[JulianCloudNTH]

Stack from ghstack (oldest at bottom):

• [ExecuTorch][WebGPU] Flatten landed-op test dirs to test/ops/test_<op>.py #20435
• [ExecuTorch][WebGPU] cat op test suite (cases.py op-test framework) #20399
• [ExecuTorch][WebGPU] Add cat op + ValueList graph support (aten.cat.default) #20398
• -> [ExecuTorch][WebGPU] permute_copy op test suite (cases.py op-test framework) #20397
• [ExecuTorch][WebGPU] Add permute_copy + IntList graph support (aten.permute_copy.default) #20396
• [ExecuTorch][WebGPU] slice_copy op test suite (cases.py op-test framework) #20395
• [ExecuTorch][WebGPU] Add slice_copy op (aten.slice_copy.Tensor) #20394
• [ExecuTorch][WebGPU] squeeze_copy + unsqueeze_copy test suites (cases.py op-test framework) #20393
• [ExecuTorch][WebGPU] Add squeeze_copy + unsqueeze_copy (flat copies) #20392
• [ExecuTorch][WebGPU] sigmoid op test suite (cases.py op-test framework) #20391
• [ExecuTorch][WebGPU] Add sigmoid op (aten.sigmoid.default) #20390
• [ExecuTorch][WebGPU] select_copy op test suite (cases.py op-test framework) #20363
• [ExecuTorch][WebGPU] Add select_copy op (aten.select_copy.int) #20362
• [ExecuTorch][WebGPU] view_copy op test suite (cases.py op-test framework) #20361
• [ExecuTorch][WebGPU] Add view_copy op (aten.view_copy.default) #20360
• [ExecuTorch][WebGPU] mul op test suite (cases.py op-test framework) #20359

Registers aten.permute_copy.default in the cases.py op-test framework: a _permute_suite of 4 configs (3D rotation, 4D middle-dim transpose, 2D transpose, full 4D shuffle) that generate_op_tests exports via VulkanPartitioner and compares to a torch golden on Dawn. Also adds test/ops/permute/test_permute.py (PermuteModule + CONFIGS + _op_delegated smoke test) and the aten.permute_copy.default partitioner-allowlist entry in tester.py.
@exported-using-ghexport

Differential Revision: D108793156

Differential Revision: D108793156

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20397

• 📄 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:

• [ROCm] MI350 CI jobs will have longer queue times due to CI migration

❌ 3 New Failures, 1 Pending, 3 Unrelated Failures

As of commit f0e9b62 with merge base 65bc0ca ():

NEW FAILURES - The following jobs have failed:

• pull / test-arm-backend-no-driver (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 9bf8898b0176cd94e6b18d23be98ee8983478abd1ff90f940c84c61fcf7f73b4 /exec failed with exit code 1
• pull / unittest / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 1cf10916015be92500c2a27e536cd2729b02f9443988b20adca639d81137a50b /exec failed with exit code 1
• pull / unittest-editable / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 31eaf442888b609f6c73b9ce84d062f78edecc2a2440b8ca7aaecf7463bafb6f /exec failed with exit code 1

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

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

• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (trunk failure)
• pull / unittest / macos / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  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.

[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.

[JulianCloudNTH]

@claude review

[claude]

Claude finished @JulianCloudNTH's task in 1m 49s —— View job

---

PR Review

• Read changed files
• Analyze for issues
• Post review

Reviewed against the sibling op-test files (slice, select, squeeze, unsqueeze) and test_suite.py / cases.py. This is a clean, consistent addition that follows the established framework conventions. No blocking issues.

Strengths

• The cases.py suite mirrors _squeeze_suite/_unsqueeze_suite exactly (construct kwarg + golden_dtype="float32" with the correct "fp64 bit-identical" rationale). Good fit.
• test_permute.py adds an extra _op_delegated assertion that the slice/select/squeeze tests lack — verifying the op is absorbed into the delegate rather than left as a top-level CPU-fallback node. That's a stronger guarantee than the siblings; nice.
• tester.py allowlist entry is in the right place and matches the edge op overload (permute_copy.default).
• Deterministic seeded input (_det_input) is consistent with the rest of the directory.

Minor notes (non-blocking)

1. test_golden_matches_eager is effectively a tautology (test_permute.py:79-84). The LHS PermuteModule(perm)(x) is torch.permute(x, perm).contiguous() and the RHS is the identical expression, so the assertion can never fail. This matches the sibling convention exactly (SliceModule(fn)(x) vs fn(x) is the same shape), and the real numeric verification happens in the generated op-test against the Dawn golden — so this is consistent, just worth being aware it isn't adding independent coverage.

2. .contiguous() in PermuteModule.forward (test_permute.py:34) — the edge permute_copy already materializes, so the trailing .contiguous() is likely redundant. Harmless, but the siblings (SliceModule/SelectModule) don't add it, so it's a small inconsistency. Fine to leave if it was intentional (e.g. to pin the output layout).

3. Extra blank line in the import block (cases.py:37) between the mul and permute imports. The surrounding import groups are inconsistently spaced already, but worth confirming lintrunner -a (usort/black) leaves this as-is before merge.

4. _op_delegated iterates all graph nodes including placeholder/output/get_attr; getattr(n, "target", "") is safe for those (returns a non-"permute" value), so the substring check is correct — just relies on no benign node carrying "permute" in its target string, which holds here.

Overall: LGTM. The only thing I'd actually verify before merge is lintrunner -a on the import block (note 3).
· branch gh/JulianCloudNTH/46/head