Add Llama3.2 CoreML ANE to benchmark

[guangy10]

Llama3.2 Core ML ANE. Require iOS 18. @huydhn created a new device pool with iOS 18+. We will run the ANE path using this device pool.

Job link: https://github.com/pytorch/executorch/actions/runs/12423590967

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7399

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 95c6cd7 with merge base 62016d6 ():
💚 Looks good so far! There are no failures yet. 💚

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

[guangy10]

@huydhn We need the ability to specify the OS version together to select devices from the device pool as some configs may require to run on/above certain OS versions. Running Llama3.2 w/ Core ML ANE requires minimal iOS 18.0 for example.

[facebook-github-bot]

@guangy10 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[huydhn]

@huydhn We need the ability to specify the OS version together to select devices from the device pool as some configs may require to run on/above certain OS versions. Running Llama3.2 w/ Core ML ANE requires minimal iOS 18.0 for example.

It could be done by creating a new device pool. I go ahead and create one ready. You can use arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2cf0f-6d9b-45ee-ba1a-a086587469e6/12c8b15c-8d03-4e07-950d-0a627e7595b4 for iPhone 15 devices with iOS >= 18.0

[guangy10]

Okay, we can see the CoreML ANE is working on iSO 18. Going to use the new device pool for this path

[facebook-github-bot]

@guangy10 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.