Arm backend: Reduce atol in vector_norm test

[oscarandersson8218]

pipeline.change_args("run_method_and_compare_outputs",...) was used to change qtol, but as no inputs were passed in the call run_method_and_compare_outputs produced new inputs with a different distribution (randn), than what was used for calibration (rand).

cc @digantdesai @freddan80 @per @zingo

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11281

• 📄 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

As of commit 71fb457 with merge base d4906e2 ():

NEW FAILURES - The following jobs have failed:

• trunk / test-llama-torchao-lowbit / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 134
• trunk / test-models-linux-aarch64 (softmax, portable, linux.arm64.2xlarge) / linux-job (gh)
  RuntimeError: Command docker exec -t 7f3d92c7ae37b2a8630a60c76375baec385d6eb7f935f67dd07946a8cf886feb /exec failed with exit code 1

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

[zingo]

Fail unrelated
[trunk / test-llama-torchao-lowbit / macos-job (push)]