Qualcomm AI Engine Direct - Change transpose output from NCH1 to NC1H before conv

[chenweng-quic]

Summary

This memory layout has better performance on the HTP backend, and lead to better performance on prefill model.

Prefill performance of third partitioned graph:

Model	w/o	w/
llama3.2 3b instruct	55924	35774

cc @cbilgin @psiddh

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21707

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures

As of commit afb0f01 with merge base b20f16a ():

NEW FAILURES - The following jobs have failed:

• Lint / link-check / lint-urls (gh)
• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh)
  RuntimeError: Command docker exec -t 89868d9fdd96a246390e06d5158a18fbecbdecc83e90a6842b88908d33e25149 /exec failed with exit code 1
• pull / test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job (gh)
  RuntimeError: Command docker exec -t 7673b0f82b3d9e085d757adba0ea21d5f7505b2371290f1837bd03553d91087d /exec failed with exit code 1
• pull / test-qnn-passes-linux / linux-job (gh)
  backends/qualcomm/tests/test_passes.py::TestPasses::test_mha_to_sha

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.