Qualcomm AI Engine Direct - Python API Refactor

[winskuo-quic]

Summary

The biggest goal of this PR is to improve user experience by maintaining consistency across all example scripts and provide an official config file for QNN APIs.
In the past, user has to manually provide params to APIs such as build_executorch_binary to make it work. However, not all the params are passed in the build_executorch_binary, making some of the flags not working, which leaves users confused. Taking example below, if user tries to skip node in script 1, it will fail.

For this reason, we want to maintain a QnnConfig structure as an official config file.
If we want to introduce a new flag to our APIs, if we want all scripts to benefit from the flag, we will need to update all our example scripts, making it hard to maintain as we support more flags and more scripts. With this feature, we don't have to manually update all example scripts when a new flag is introduced. Instead, all QnnConfig will parse it itself and we don't have to update the example script at all.

This PR does the following:

1. Introduce QnnConfig, which takes parser or .json file as input
2. Migrate our Qnn ExecuTorch official APIs to backends/qualcomm/export_utils.py. The reason of doing this is API calls shouldn't be under examples folder. Furthermore, pip install executorch does not include examples/qualcomm folder, meaning these APIs are not exposed to users that uses pip install.
3. The following flags can now all be removed from example scripts and backend API will handle the logic: compile_only, pre_gen_pte, skip_push, profile_level, dump_intermediate_outputs, shared_buffer, skip_delegate_node_ids, skip_delegate_node_ops.
4. Update README so it aligns with the new behavior.

Test plan

Passes all tests under test_qnn_delegate.py.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18312

• 📄 Preview Python docs built from this PR

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

⏳ 4 Pending, 3 Unrelated Failures

As of commit 4a6594d with merge base ca2a616 ():

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.
• trunk / unittest-release / 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.