[billmguo]

Summary:
//executorch/examples/qualcomm/oss_scripts/llama:llama_qnn currently fails at import time for every model, before any argument is parsed, with ModuleNotFoundError: No module named 'executorch.examples.models.gemma4' and then ... granite_speech. The Buck targets drifted from the sources synced from upstream: the Gemma4 enablement (#20979) added an unconditional executorch.examples.models.gemma4 import with no owning target for gemma4/__init__.py, Granite-Speech added model/audio_encoder.py plus a granite_speech import, and QAD (#21036) added quantize/qat.py, dataset/{constants,targets}.py and the train/ package, none of which are in any target.

This adds a gemma4 library owning gemma4/__init__.py, a new train library (including its train/config/*.yaml resources), the missing sources in static_llama, dataset and quantize, and the gemma4 and granite_speech deps on llama_lib. The fbcode/ and xplat/ copies are kept byte-identical.

Known limitation, not addressed here: under Buck QNN_SDK_ROOT is a placeholder, so is_qnn_sdk_version_less_than("2.35") cannot detect the SDK version and masked softmax is disabled during export even though the pinned SDK (2.50) supports it.

Authored with Claude Code.

Differential Revision: D127006045

cc @cbilgin @psiddh

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24100

• 📄 Preview Python docs built from this PR

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

❌ 36 Pending, 2 Unclassified Failures

As of commit b704557 with merge base 71a713c ():

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

• Build Windows Wheels / pytorch/executorch / build-wheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
• Build Windows Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cpu (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found

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

[meta-codesync]

@billmguo has exported this pull request. If you are a Meta employee, you can view the originating Diff in D127006045.

[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.