Arm backend: Add support for QAT+per-channel combo

[oscarandersson8218]

Fixes a bug where an unsupported observer was used for QAT combined with per-channel quantization.

cc @digantdesai @freddan80 @per @zingo

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13511

• 📄 Preview Python docs built from this PR

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

❌ 10 New Failures, 1 Cancelled Job, 4 Unrelated Failures

As of commit 8d3c2e7 with merge base 85e5b6e ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-editable / linux / linux-job (gh)
  backends/xnnpack/test/passes/test_channels_last_tagged_reshape.py::TestChannelsLastTaggedReshapePass::test_q_dq_nodes_around_copy_are_tagged
• trunk / test-huggingface-transformers-coreml (gemma3-1b|xnnpack|--quantize) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 139
• trunk / test-huggingface-transformers-coreml (llama3.2-1b|xnnpack|--quantize) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 139
• trunk / test-huggingface-transformers-coreml (phi4-mini|xnnpack|--quantize) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 138
• trunk / test-huggingface-transformers-coreml (qwen3-0.6b|xnnpack|--quantize) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 138
• trunk / test-huggingface-transformers-coreml (smollm2-135m|xnnpack|--quantize) / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 138
• trunk / test-models-arm-zephyr (add) / linux-job (gh)
  RuntimeError: Command docker exec -t 8818dd519fa984d11cb6490ed79d7dad49258b39e146fa4da3be5be546286e1b /exec failed with exit code 1
• trunk / test-models-arm-zephyr (mv2) / linux-job (gh)
  RuntimeError: Command docker exec -t c14420426aa12e970a00804beec6cd79eac39247e66136a906387197c420c9c8 /exec failed with exit code 1
• trunk / test-models-arm-zephyr (softmax) / linux-job (gh)
  RuntimeError: Command docker exec -t eadbb77e6fa47c9206003c4003afeb0c9fd5099854e963d7179a6cdb15b83cc9 /exec failed with exit code 1
• trunk / unittest-release / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 8

CANCELLED JOB - The following job was cancelled. Please retry:

• Check Labels (gh)

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

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

• pull / test-vulkan-models-linux / linux-job (gh) (trunk failure)
  /pytorch/executorch/backends/vulkan/runtime/graph/ComputeGraph.cpp:885:20: error: redefinition of 'prepare_pipelines'
• pull / unittest / linux / linux-job (gh) (trunk failure)
  /pytorch/executorch/backends/vulkan/runtime/graph/ComputeGraph.cpp:885:20: error: redefinition of 'prepare_pipelines'
• trunk / test-huggingface-transformers-coreml (olmo-1b|coreml_fp32_gpu|--quantize) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• trunk / unittest-release / linux / linux-job (gh) (trunk failure)
  /pytorch/executorch/backends/vulkan/runtime/graph/ComputeGraph.cpp:885:20: error: redefinition of 'prepare_pipelines'

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

[digantdesai]

Don't we need a FakeQuantize variant of this observer with qat?

[oscarandersson8218]

Yes, you're right. Will look into a fix and proper testing of QAT.

[oscarandersson8218]

Fixed here #14001