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.

Reviewed By: JakeStevens

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.

❗ 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

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

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: apullin / name: Andrew Pullin (baf29c1)

[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]

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

[apullin]

Something wrong with internal/external sync. No idea. Closing. Will try to regenerate.