ExtensionLLM: Make it possible to pass memory mode for the Ethos-U

[gggekov]

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19450

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 1 Pending, 1 Unrelated Failure

As of commit 88e7dd2 with merge base d939b9b ():

NEW FAILURES - The following jobs have failed:

• pull / unittest / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv2_model
• trunk / unittest-release / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv2_model

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

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

• pull / test-moshi-linux / linux-job (gh) (trunk failure)
  E: Failed to fetch http://security.ubuntu.com/ubuntu/pool/main/o/openjpeg2/libopenjp2-7_2.4.0-6ubuntu0.4_amd64.deb 404 Not Found [IP: 104.20.28.246 80]

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.

[Copilot]

Pull request overview

This PR extends the ExtensionLLM Arm/Ethos‑U export flow to allow propagating Ethos‑U Vela configuration options (system configuration and memory mode) into the Ethos‑U partitioner so users can control these settings from LlmConfig.

Changes:

• Extend get_ethosu_partitioner() to accept system_config and memory_mode, and translate the LLM config sentinel "default" to None for EthosUCompileSpec.
• Update Llama Arm lowering to pass llm_config.backend.ethosu.system_config and .memory_mode into get_ethosu_partitioner().

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
extension/llm/export/partitioner_lib.py	Adds system_config/memory_mode parameters to the Ethos‑U partitioner helper and normalizes "default" to None.
examples/models/llama/export_llama_lib.py	Passes Ethos‑U system_config/memory_mode from LlmConfig into the Ethos‑U partitioner during lowering.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[zingo]

OK to merge only touch Arm code paths in this example and does not change buck2 stuff.