Qualcomm AI Engine Direct - Fix Full

[winskuo-quic]

Summary

Based on reported issue: #19179
2 mathematically equivalent model in nn.Module lowered both lowered to QNN, however, 1 accuracy is good while another is bad. Debugged with qnn_intermediate_debugger and targeted that accuracy drop is possibly caused by full operation. Took a look and noticed the op builder did not take layout transform into consideration.

Test plan

Passing tests under test_qnn_delegate.py and fix issue in: #19179

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19359

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 17 Unrelated Failures

As of commit f603e89 with merge base af90130 ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 2e5d6316437492687f8585c6a0b071763e8847cddbafd983b2a8bc2ba21998cc /exec failed with exit code 1
• pull / unittest-editable / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv3_model

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

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

• pull / test-lora-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-lora-multimethod-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-models-linux (ic4, portable, linux.4xlarge.memory) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-models-linux (ic4, xnnpack-quantization-delegation, linux.4xlarge.memory) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-models-linux (mobilebert, portable, linux.2xlarge) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-models-linux (mobilebert, xnnpack-quantization-delegation, linux.2xlarge) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-models-linux (phi_4_mini, portable, linux.4xlarge.memory) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-moshi-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-phi-3-mini-runner-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-sqnr-static-llm-qnn-linux (smollm2_135m) / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-voxtral-realtime-xnnpack-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-vulkan-models-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest / linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest / macos / macos-job (gh) (trunk failure)
  [ FAILED ] OpGridSampler2dTest.BatchSizeMismatchDies
• pull / unittest / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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.

[digantdesai]

Any test to prevent future regression?

[winskuo-quic]

Any test to prevent future regression?

@digantdesai Thanks for reviewing the PR. I have added some UTs that will fail without this change and passes with this PR.