Qualcomm AI Engine Direct - Move QCOM_AXIS_ORDER pop into LayoutTransform pass

[paul1106]

Context

This PR supersedes #21630.

The original PR was closed due to CLA issues.
This new PR is created from a new branch to track CLA status and continue the review process.

Please refer to #21630 for previous review comments and discussion.

Summary:

• The pop of QCOM_AXIS_ORDER was previously done in
  QnnBackend._build_op_wrappers before calling
  transform_for_preprocess_pipeline. Moving it into
  LayoutTransform.call() when insert_permute=True keeps the cleanup
  logic co-located with the code that depends on it.

• The pop is necessary because the delegated subgraph is created via
  deepcopy, which carries over the QCOM_AXIS_ORDER tags written by the
  to-edge LayoutTransform run. Without clearing them, is_transformed_node()
  returns True for every sensitive node in the
  main for-loop, causing all traversals to be skipped and no permute
  nodes to be inserted.

Test plan

python -m backends.qualcomm.tests.test_qnn_delegate TestQNNQuantizedOperator  --device ${SERIAL_NUM}   --soc_model ${SOC_MODEL}   --build_folder build-android   --executorch_root .

cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin @abhinaykukkadapu @psiddh

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21932

• 📄 Preview Python docs built from this PR

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

⚠️ 13 Awaiting Approval

As of commit f701d62 with merge base b45e85d ():

AWAITING APPROVAL - The following workflows need approval before CI can run:

• Build documentation (gh)
• Build Presets (gh)
• Cadence Build & Test (gh)
• Lint (gh)
• periodic (gh)
• pull (gh)
• Test ARM Backend (gh)
• Test CoreML Backend (gh)
• Test QNN Backend (gh)
• Test QNN Windows MSVC build (gh)
• Test Vulkan Backend (gh)
• Test WebGPU Backend (gh)
• Test XNNPACK Backend (gh)

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[meta-cla]

Hi @paul1106!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[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.

[Copilot]

Pull request overview

This PR relocates cleanup of the QCOM_AXIS_ORDER node metadata from QnnBackend._build_op_wrappers into the LayoutTransform pass itself (specifically when insert_permute=True), so the metadata invalidation happens next to the logic that depends on it. This prevents inherited QCOM_AXIS_ORDER tags (carried via deepcopy) from making LayoutTransform.is_transformed_node() incorrectly treat all sensitive nodes as already-processed, which would otherwise suppress permute insertion during preprocessing.

Changes:

• Remove the QCOM_AXIS_ORDER metadata pop from backends/qualcomm/qnn_preprocess.py preprocessing entrypoint.
• Add a targeted QCOM_AXIS_ORDER metadata pop inside LayoutTransform.call() when running the permute-inserting mode (insert_permute=True).

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
backends/qualcomm/qnn_preprocess.py	Removes early QCOM_AXIS_ORDER meta cleanup from _build_op_wrappers, delegating it to the pass that relies on it.
backends/qualcomm/_passes/layout_transform.py	Clears inherited QCOM_AXIS_ORDER tags before the main sensitive-node traversal when insert_permute=True, ensuring permute insertion logic executes.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[paul1106]

This PR supersedes #21630.

The original PR was closed due to CLA issues.
This new PR is created from a new branch to track CLA status and continue the review process.

Please refer to #21630 for previous review comments and discussion.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.