Add xnnpack-no-sme2 flavor to Android release workflow

[kirklandsign]

Summary

Add option to disable ARM SME2 for Android emulator compatibility, which may crash when SME2 kernels are used.

Test plan

CI

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16589

• 📄 Preview Python docs built from this PR

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

❌ 24 New Failures, 4 Unrelated Failures

As of commit 3580356 with merge base f39016d ():

NEW FAILURES - The following jobs have failed:

• pull / test-coreml-bc-macos (macos-m2-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / unittest / windows / windows-job (gh)
  Process completed with exit code 1.
• pull / unittest-editable / windows / windows-job (gh)
  Process completed with exit code 1.
• Test CUDA Builds / check-all-cuda-builds (gh)
  Process completed with exit code 1.
• Test CUDA Builds / export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 13f2c24b6bb04741f653f8f7120f2ff2dcbecd54330e3e3afa5f62b82ff72396 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 575c5586c6bc7320aea7a03702512371f0b25ccc7e8886ad8bc93a5b6924e3c1 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 4985b8d984a71245b15191428567461717bfb721c30b96c5c06e25999c37d86e /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 6b6db0532149205f489bd6142b945d1af01b647b95a99856cb2cd431642578b6 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t a09cda1ee3e34a510e20ab68977821f5bb9efb7ed6f4b5c430f7ff9b1fddf4df /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t ffc63e1b29a51ebdf31b82f9c01a8a260eccb5d4908254a98e994c2ad56af7d4 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 46ee5eccfc82aff46744c71dadc88ae466185456e37365a09f35ff5b5609f0ee /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t 97c662e59d20fd7cbee7abeacdda86e09129f25f300635949b991d5b7fb6a6b5 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 4f5b7b69238d1761c827b5d60529e9e2a2d88c369dbaca25b7511c42df30c703 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 42381dad2673e8f3924ad13a999280540c4527497332e9401a22bfa25b4244dd /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t 5bcd721d9c088d81d264d4a3f1c72aeef700dc74c6818692322c09ec161a897c /exec failed with exit code 1
• Test CUDA Builds / test-executorch-cuda-build-12.6 / linux-job (gh)
  RuntimeError: Command docker exec -t e2958da36ccc9ba9d95d04f85121652b72f6c1e8c3eeac10fe41b2e1d0c64595 /exec failed with exit code 1
• Test CUDA Builds / test-executorch-cuda-build-12.8 / linux-job (gh)
  RuntimeError: Command docker exec -t e7f09bea97b87f11836e3b24f563604255c05cbf6a7dade4ee266ef5faa4c3e9 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (add_mul) / linux-job (gh)
  RuntimeError: Command docker exec -t e86151d89c4e77d6ef2f43b5742f6f897f44b9d5cf0eeb36e525297a2eee24f7 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (add) / linux-job (gh)
  RuntimeError: Command docker exec -t 197020d3884e66e038dcfe2843dac5ee6a681ec11dcaa52f3a1525a32bae290d /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (conv1d) / linux-job (gh)
  RuntimeError: Command docker exec -t 0f819150137d321a1d14e9768cfa844df2b96d02114c0c7d7836bde0899afe9e /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (linear) / linux-job (gh)
  RuntimeError: Command docker exec -t 0cc66c443b965ff03b954030ea8a6ee5e8f6a38a91726f3e85164547ebf7ecaf /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (resnet18) / linux-job (gh)
  RuntimeError: Command docker exec -t 0d5405e3e5c921412ce2dccfb44a37b9e90c3a0e1f9c94c70efdb8bbf8ff6bab /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (sdpa) / linux-job (gh)
  RuntimeError: Command docker exec -t f7ca0efb955cfa5a81692469b0a8a2aa3b1941072d99c143938269f389bff6f1 /exec failed with exit code 1
• Test CUDA Builds / unittest-cuda / linux-job (gh)
  RuntimeError: Command docker exec -t 6ca281d677cea9c9ac5f164c76b00131a13773271480d4a05904b934edc26911 /exec failed with exit code 1

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• Test Metal Backend / export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job (gh) (similar failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test Metal Backend / export-model-metal-artifact (openai, whisper-large-v3-turbo, non-quantized) / macos-job (gh) (similar failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test Metal Backend / export-model-metal-artifact (openai, whisper-small, non-quantized) / macos-job (gh) (similar failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

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

• Test Metal Backend / test-executorch-metal-build / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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 pull request adds support for disabling ARM SME2 instructions in the Android release workflow to ensure compatibility with Android emulators that may crash when SME2 kernels are used.

Changes:

• Added a new "xnnpack-no-sme2" flavor option to the Android release workflow
• Introduced the XNNPACK_ENABLE_ARM_SME2 configuration flag (defaulting to ON) that can be overridden
• Added documentation explaining when and why to disable SME2

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
.github/workflows/android-release-artifacts.yml	Added "xnnpack-no-sme2" flavor option and conditional logic to disable SME2 when this flavor is selected
scripts/build_android_library.sh	Added XNNPACK_ENABLE_ARM_SME2 environment variable (defaulting to ON) and passed it to CMake configuration
backends/xnnpack/cmake/Dependencies.cmake	Added documentation comments explaining the ARM SME2 flag and when it should be disabled

---

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

[GregoryComer]

It's odd that it's crashing on emulator. I can try to take a look and we can fix the underlying issue, but I'm fine to just disable it for now.

[kirklandsign]

It's odd that it's crashing on emulator. I can try to take a look and we can fix the underlying issue, but I'm fine to just disable it for now.

GPT says something to do with emulator support on Apple Silicon.