Update examples/models/llama/README.md to fix build broken

[DamonFool]

Fix the following error

CMake Error at tools/cmake/common/preset.cmake:122 (message):
  Use of 'EXECUTORCH_BUILD_EXTENSION_MODULE' requires
  'EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR'
Call Stack (most recent call first):
  tools/cmake/preset/default.cmake:300 (check_required_options_on)
  CMakeLists.txt:87 (include)

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12393

• 📄 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, 4 Unrelated Failures

As of commit efbf137 with merge base a0618c8 ():

NEW FAILURE - The following job has failed:

• pull / test-eval_llama-mmlu-linux / linux-job (gh)
  RuntimeError: Command docker exec -t a6b999a08f62fe9a7dbdee43b160a59365c8005fa71ea9c8f10602990b4e32ea /exec failed with exit code 1

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest / linux / linux-job (gh) (trunk failure)
  devtools/inspector/tests/inspector_utils_test.py::TestInspectorUtils::test_equip_debug_handle_to_export_program_success
• pull / unittest / macos / macos-job (gh) (trunk failure)
  devtools/inspector/tests/inspector_utils_test.py::TestInspectorUtils::test_equip_debug_handle_to_export_program_success
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  devtools/inspector/tests/inspector_utils_test.py::TestInspectorUtils::test_equip_debug_handle_to_export_program_success
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  devtools/inspector/tests/inspector_utils_test.py::TestInspectorUtils::test_equip_debug_handle_to_export_program_success

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

[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.

[lucylq]

Hi @DamonFool, thanks for submitting this PR. I don't think llama build should require flat_tensor - is the repro command exactly from the readme/could you provide instructions for your repro?

[DamonFool]

Hi @DamonFool, thanks for submitting this PR. I don't think llama build should require flat_tensor - is the repro command exactly from the readme/could you provide instructions for your repro?

Thanks @lucylq for taking a look at this.
Yes, I just followed the steps in the readme and copied commands in it.

The logic is that llama requires EXECUTORCH_BUILD_EXTENSION_MODULE, which requires EXECUTORCH_BUILD_EXTENSION_FLAT_TENSOR.

The cmake error msg has showed that dependency clearly.
You can verify it by testing the commands it the readme.
Thanks.

[DamonFool]

I don't think llama build should require flat_tensor

Hi @lucylq , After #11457 , flat_tensor is required.
Please also see https://github.com/pytorch/executorch/blob/main/tools/cmake/preset/default.cmake#L305 .
Thanks.

[lucylq]

I don't think llama build should require flat_tensor

Hi @lucylq , After #11457 , flat_tensor is required. Please also see https://github.com/pytorch/executorch/blob/main/tools/cmake/preset/default.cmake#L305 . Thanks.

Hi @DamonFool , thank you for the PR link! I added #12514 to remove FLAT_TENSOR when it's not needed. I think that was added in to ensure all the builds work when we were adding cmake presets; it should be removed now that things are more stable.

[lucylq]

Thanks for making this PR @DamonFool.

I was mistaken, and flat_tensor is required as a dependency of extension_module.

[DamonFool]

Thanks @lucylq .
The 5 cicd failures should not be related to this patch since this is only a doc change, right?

[DamonFool]

Hi @lucylq , are you fine to merge this pr?
Thanks.

[DamonFool]

Thanks @lucylq .