Qualcomm AI Engine Direct - Fixed Conv2d + PReLu fusion issue

[shewu-quic]

Summary:

• There is a constraint to fuse Conv2d and PRelu
  • the coefficient must be a scalar (1x1x1x1) or (1x1x1xd) for fusion, and it will be broadcasted by QNN HTP.
  • The htp_arch is greater than 73
  • The H and W of weight shape is less than 8
• Add the test cases to check the fusion is successful

Test Plan:

python backends/qualcomm/tests/test_qnn_delegate.py TestQNNQuantizedModel.test_qnn_backend_conv2d_leaky_relu_fusion -H {HOST} -s {SERIAL} -m SM8750 -b build-android -a /path/to/executorch_artifacts

python backends/qualcomm/tests/test_qnn_delegate.py TestQNNQuantizedModel.test_qnn_backend_conv2d_relu_fusion -H {HOST} -s {SERIAL} -m SM8750 -b build-android -a /path/to/executorch_artifacts

python backends/qualcomm/tests/test_qnn_delegate.py TestQNNQuantizedModel.test_qnn_backend_linear_leaky_relu_fusion -H {HOST} -s {SERIAL} -m SM8750 -b build-android -a /path/to/executorch_artifacts

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19014

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (2 Unrelated Failures)

As of commit d1cb046 with merge base 2d53535 ():

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

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

• pull / unittest / windows / windows-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.

[abhinaykukkadapu]

@shewu-quic can you rebase the diff, wondering why the newly added buck and pass tests are failing specifically on this diff.