Enable per-row/per-col grouping in CoreML LUT ops

[metascroy]

This PR enables per-row grouping in CoreML LUT ops.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13674

• 📄 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 MI2xx CI/CD workflows failing due to : download from https://api.github.com/repos/pytorch/pytorch timed out.

❌ 2 New Failures, 1 Unrelated Failure

As of commit 3a826fd with merge base 0d0769a ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  At least one of the pre-conditions you specified did not hold
• trunk / unittest-release / macos / macos-job (gh)
  backends/xnnpack/test/recipes/test_xnnpack_recipes.py::TestXnnpackRecipes::test_int8_static_quant_recipe

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

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

• pull / unittest-nxp-neutron / linux-job (gh) (trunk failure)
  test_split_group_convolution__applied_by_default

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.

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80995383.

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80995383.

[YifanShenSZ]

LGTM! Thanks for adding more LUT support!

One quick question though: In CoreML LUT we allow arbitrary vector axis, is there a reason in torch we support only row or col?

[metascroy]

LGTM! Thanks for adding more LUT support!

One quick question though: In CoreML LUT we allow arbitrary vector axis, is there a reason in torch we support only row or col?

This is still scalar-valued LUT (vector axis is for vector-valued LUT, which is still not supported).

The row/col here refer to the granularity of the LUTs as discussed here: https://apple.github.io/coremltools/docs-guides/source/opt-palettization-overview.html

The diagram for "per-grouped channel lookup table" corresponds to per-row grouping.

If the original tensor has size (n, k), we can support 1 LUT per col_group_size columns (can be specified with block_size = [-1, col_group_size], where -1 is interpreted as n), or we can support 1 LUT per row_group_size rows (can be specified as block_size = [row_group_size, -1], where -1 is interpreted as k).

[metascroy]

@cccclai @digantdesai can I get a stamp for ET to merge?

[facebook-github-bot]

@metascroy has imported this pull request. If you are a Meta employee, you can view this in D80995383.