Channels last: preserve metadata across op replacement

[rascani]

Stack from ghstack (oldest at bottom):

• Cortex-M: add opt-in explicit layout lowering #21928
• Cortex-M: add explicit-NHWC runtime operators #21927
• Cortex-M: share layout-aware CMSIS-NN kernels #21926
• Channels last: add the common layout pipeline #21925
• Channels last: optimize structural layout regions #21924
• -> Channels last: preserve metadata across op replacement #21923

Preserve the complete metadata dictionary when replacing an ATen operator with its channels-last dialect counterpart. ExportPass retracing recomputes layout-dependent shape fields such as val and tensor_meta, while source attribution and backend annotations such as debug_handle, from_node, input_qparams, output_qparams, and custom metadata survive the rewrite.

Document the remaining caller contract in terms of every input and output listed by ChannelsLastOpSpec. Semantic metadata tied to a permuted dimension, such as a per-channel quantization axis, must be rejected or remapped by the backend before replacement. This keeps provenance preservation as the default without implying that a metadata allowlist validates layout semantics.

Keep structural-layout helper definitions out of this change; the following optimizer Diff introduces them when they gain multiple consumers. Convert the existing Buck test target to pytest-aware discovery and add coverage for provenance survival together with recomputed NHWC output shape.

Differential Revision: D116372280

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21923

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures

As of commit 06f4f6d with merge base ed2d9ec ():

NEW FAILURES - The following jobs have failed:

• pull / test-qnn-buck-build-linux / linux-job (gh)
  RuntimeError: Command docker exec -t f83fef9c539cf513fc5b110f7ece49313a7064fff08bae0e4b11b8b848c2bc63 /exec failed with exit code 3
• pull / unittest-buck / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 2d3148a8b5b684df535ab4f2303b592213a008e86004a66db54fce3ec89a8b46 /exec failed with exit code 3
• pull / unittest-buck / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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.