build: bump executorch to v1.2.0

[barhanc]

Description

Updates ExecuTorch binaries and header files to version v1.2.0

Introduces a breaking change?

• Yes
• No

Type of change

• Bug fix (change which fixes an issue)
• New feature (change which adds functionality)
• Documentation update (improves or adds clarity to existing documentation)
• Other (chores, tests, code style improvements etc.)

Tested on

• iOS
• Android

Testing instructions

• Run tests from packages/react-native-executorch/common/rnexecutorch/tests.
• Build all example apps on both Android and iOS and verify that models work as expected.

Screenshots

Related issues

Closes #1057

Checklist

• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have updated the documentation accordingly
• My changes generate no new warnings

Additional notes

The binaries were built from https://github.com/barhanc/executorch/tree/rne-build-v1.2.0. The header files also come from there.

[benITo47]

From what I tested - models on iOS work. Had some issues with building LLM demo app due to audio-api throwing an error - maybe a version bump would help?
Will test Android tomorrow

[IgorSwat]

I tested Android - no issues found. I think we can merge it safely.

[msluszniak]

@barhanc one small thing. Could you test if Bielik model from our HuggingFace works on android? If you get: E Missing operator: [12] torchao::_linear_8bit_act_4bit_weight.out would you be able to rebuild android libs so they have custom torchao ops?

Or maybe the reason is that the model was exported with ExecuTorch 1.0.0 and now is not compatible. Since most (if not all) of the re-exported llms uses 8 bit activation 4 bit weights it's strange that this particular model does not work on android.

EDIT: I successfully built this op in arm64 and model ran on android (device that supports ARMv8.4+, e.g. One+ 12) and later for ARMv8.2+ np. FYI: the changes for version ARMv8.4+ are on the first commit and for ARMv8.2+ on the second commit on this branch: https://github.com/software-mansion/react-native-executorch/tree/msluszniak/torchao-4bit-android

[barhanc]

@barhanc one small thing. Could you test if Bielik model from our HuggingFace works on android? If you get: E Missing operator: [12] torchao::_linear_8bit_act_4bit_weight.out would you be able to rebuild android libs so they have custom torchao ops?

Or maybe the reason is that the model was exported with ExecuTorch 1.0.0 and now is not compatible. Since most (if not all) of the re-exported llms uses 8 bit activation 4 bit weights it's strange that this particular model does not work on android.

EDIT: I successfully built this op in arm64 and model ran on android (device that supports ARMv8.4+, e.g. One+ 12) and later for ARMv8.2+ np. FYI: the changes for version ARMv8.4+ are on the first commit and for ARMv8.2+ on the second commit on this branch: https://github.com/software-mansion/react-native-executorch/tree/msluszniak/torchao-4bit-android

The problem with Bielik was connected to the previous export of the model. I've re-exported the model and updated it on HF. It should work now without requiring the fix.