Arm backend: Relax Qwen3 VL BF16 tolerance on Arm64

[zingo]

Increase the TOSA BF16 atol for the Qwen3 VL full vision-model test on aarch64 only.

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

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20450

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• [ROCm] MI350 CI jobs will have longer queue times due to CI migration

❌ 4 New Failures, 2 Unrelated Failures

As of commit 7cb9a05 with merge base 0fe2607 ():

NEW FAILURES - The following jobs have failed:

• Apple / build-frameworks-ios / macos-job (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh)
  RuntimeError: Command docker exec -t 5db8efc447e712b03302028b0988f72dc12751898c02a41e1de3a86703e37c0a /exec failed with exit code 92
• trunk / test-qnn-optimum-model (fp32, efficientnet) / linux-job (gh)
  RuntimeError: Command docker exec -t 5d055691f4ea51f06e9932d3a3e1a708a90ab197f2caf855bd78c8559ab92820 /exec failed with exit code 92
• trunk / test-qnn-optimum-model (fp32, roberta) / linux-job (gh)
  RuntimeError: Command docker exec -t a57bceba260bb028d93a9d260edf22462bf0e530e2b7de195126f0c9f15eb69c /exec failed with exit code 92

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-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (trunk failure)
• trunk / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (trunk failure)

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

[Copilot]

Pull request overview

Adjusts Arm backend TOSA BF16 numeric tolerance for the Qwen3 VL vision full-model test when running on Arm64 hosts, to accommodate observed aarch64-specific BF16 mismatches while keeping non-aarch64 behavior unchanged.

Changes:

• Introduces an aarch64-only relaxed atol (0.4) for the vision-model BF16 TOSA pipeline.
• Keeps the default BF16 tolerance for other cases at atol=0.1, rtol=0.1.

---

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

[zingo]

Test fails are unrelated