Quantize moveaxis/movedim so they delegate to Ethos-U (#20314)

[apullin]

Summary:

The ARM PT2 quantizer's pass-through shared-qspec set in quantization_annotator.py
(_one_to_one_shared_input_qspec) covers permute/permute_copy/transpose/view/squeeze
etc., but omits aten.moveaxis/aten.movedim. A model that uses torch.moveaxis
therefore leaves those ops unquantized: the quantizer brackets each one with
dequantize -> moveaxis(float) -> quantize.

On lowering, moveaxis decomposes to a float permute_copy. The Ethos-U55
operator-support check (operator_support/ethos_u55_support.py) only delegates
permute_copy for int8/int16/int32, so it rejects the float one. Each rejected
permute is stranded on the host, splitting the model into many delegated
partitions (one NPU island per permute), which bloats the .pte with per-partition
delegate overhead and host round-trips.

Add aten.moveaxis.int / aten.movedim.int to _one_to_one_shared_input_qspec
(guarded with getattr for torch-build variance, mirroring the existing
transpose.Dimname handling) so they share the input quantization spec exactly like
transpose/permute. They then stay int8, decompose to int8 permute_copy, and
delegate to the NPU -- eliminating the host float islands.

Impact: a quantized example ensemble (ConvNeXt-style blocks that
use torch.moveaxis) that previously lowered into 9 Ethos-U55 partitions now lowers
into a single delegate, with zero host permutes and ~24% smaller .pte, with no
model changes. Generalizes to any moveaxis/movedim-using model on the Ethos-U
backend.

Differential Revision: D108478011

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20314

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures, 6 Unrelated Failures, 1 Unclassified Failure

As of commit 2658037 with merge base 5241b4e ():

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
• pull / unittest / linux / linux-job (gh)
  RuntimeError: Command docker exec -t cfccef10db5ab8d7549d941d8c79650048e5537dee95a27504032a4d187e15b6 /exec failed with exit code 1
• pull / unittest-editable / linux / linux-job (gh)
  RuntimeError: Command docker exec -t fd5b11d850337822233a35099b8553490f2e127705a90a4eb021e062ed3a948e /exec failed with exit code 1
• trunk / unittest-release / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 901df83a08b563076bef27301255206c8f145604d465b4a649219ea96c9a581b /exec failed with exit code 1

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:

• trunk / test-models-macos-coreml (edsr) / macos-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  ##[error]The operation was canceled.

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• trunk / test-llama-runner-mac (fp32, coreml) / macos-job (gh) (similar failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

BROKEN TRUNK - The following jobs failed but was 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
• trunk / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (trunk failure)
• trunk / unittest-release / 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.

[linux-foundation-easycla]

• ❌ The email address for the commit (2658037) is not linked to the GitHub account, preventing the EasyCLA check. Consult this Help Article and GitHub Help to resolve. (To view the commit's email address, add .patch at the end of this PR page's URL.) For further assistance with EasyCLA, please visit our EasyCLA portal and chat with our support bot.

[meta-codesync]

@apullin has exported this pull request. If you are a Meta employee, you can view the originating Diff in D108478011.

[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.

[JakeStevens]

Please add a test for the new annotation.

It would be nice to show that this results in a lowerable chain for a simple model, I believethere are model-level tests in the backend as well

[apullin]

Added a model level test in test_moveaxis_u55_INT - although maybe that is too simple?

[JakeStevens]

Do we need this? We are explicitly saying run_on_fvp=False, so why7 fail if no corstone?

[JakeStevens]

nit: logically this should go somewhere like:

arm/test/quantizer/test_generic_annotater.py

[JakeStevens]

let's see what that CI looks like when branch is no longer out of date before landing, the tosa errors are giving me pause so make sure they are resolved