Qualcomm AI Engine Direct - supprot SAR2230P

[haowhsu-quic]

Summary

• add soc SAR2230P

Test plan

cd $EXECUTORCH_ROOT/examples
python qualcomm/scripts/export_example.py --model_name mul --output_folder . --generate_etrecord --soc SAR2230P -q ptq

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15437

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• Long queue for ROCM runners, also B200 and XPU queueing is observed

✅ No Failures

As of commit 541826c with merge base efc2be7 ():
💚 Looks good so far! There are no failures yet. 💚

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

[haowhsu-quic]

@pytorchbot label "release notes: qualcomm"

[billmguo]

@cccclai can u help review, the similar the PR break lots of test last time not sure whether we need re-export model to unblock the test or not

[cccclai]

Should we bump the qnn version before merging this PR? @billmguo mentioned that it only supports after 2.39

[billmguo]

We can keep qnn bump later since qnn-2.37 is being deployed with multiple products. The challenge parts here is for the v81 support if need custom ops support also need bump up the hexagon to 6.4.0.0, can you have dynamic qnn version support for different products?

[cccclai]

Can you rebase? Let's check CI signal

[cccclai]

import seems still failing, mind rebasing on the latest main?