Set EXECUTORCH_BUILD_QNN=ON for benchmarking app build

[kirklandsign]

Runtime change. When we build the minibench app (the AAR component) we always integrate QNN backend support into it

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5315

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 709e5ac with merge base bcd156b ():

NEW FAILURE - The following job has failed:

• pull / unittest / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

[facebook-github-bot]

@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[guangy10]

Can you add a bit more context for this fix? Is the fix for AOT or runtime? Is it because the runtime will set EXECUTORCH_BUILD_QNN=OFF by default? I thought we will always to turn it on regardless it's for QNN or XNN

[kirklandsign]

Can you add a bit more context for this fix? Is the fix for AOT or runtime? Is it because the runtime will set EXECUTORCH_BUILD_QNN=OFF by default? I thought we will always to turn it on regardless it's for QNN or XNN

Runtime. Oh that's a good point.

[facebook-github-bot]

@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[guangy10]

Can you add a bit more context for this fix? Is the fix for AOT or runtime? Is it because the runtime will set EXECUTORCH_BUILD_QNN=OFF by default? I thought we will always to turn it on regardless it's for QNN or XNN

Runtime. Oh that's a good point.

Yeah, we don't want to add complexity to build the benchmark app. It should be just one flavor with all platform supported delegates for all models.

[facebook-github-bot]

@kirklandsign merged this pull request in 4b3f1c5.