Qualcomm AI Engine Direct - issue fix #2

[haowhsu-quic]

Summary

• Conformer model fails to lower on QNN #14048 > add quantized test case with GLU decomposition
• Convnext model fails to lower on QNN #14049 > add e2e example where constant expansion is applied
• Maxvit_t model lowering segfaults on QNN #14050 > add e2e example and source transform for 6D operation
• Vit_b_16 model fails to lower on QNN #14051 > add e2e example and complement missed annotation
• Swin_v2_t model fails to lower on QNN #14052 > add e2e example and dedicated passe for 6D partition

Fixes #14048
Fixes #14049
Fixes #14050
Fixes #14051
Fixes #14052

Test plan

MATRIX = {convnext_small, maxvit_t, swin_v2_t, vit_b_16}

python backends/qualcomm/tests/test_qnn_delegate.py TestExampleOssScript.test_${MATRIX} -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/ -i /path/to/imagenet_1k/imagenet-mini/val -r .

python backends/qualcomm/tests/test_qnn_delegate.py TestQuantizedModel.test_qnn_backend_conformer -b build-android/ -m SM8750 -s $SN -a /path/to/test_artifacts/

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14378

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit d14e489 with merge base 56659e4 ():
💚 Looks good so far! There are no failures yet. 💚

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]

@cccclai has imported this pull request. If you are a Meta employee, you can view this in D82651145.

[cccclai]

Thanks for the fix! I think we may need some logics to block lowering rank-6 shape, because users may not know how to do it themselves

[facebook-github-bot]

@cccclai has imported this pull request. If you are a Meta employee, you can view this in D82651145.

[mergennachin]

@haowhsu-quic Do you want to include this in release/1.0 branch? If so, please follow instructions in #14288

Similar to #14328