NXP backend: Add QuantizeFusedConvBnBiasAtenPass call to integration tests pipeline

[StrycekSimon]

Adds call to QuantizeFusedConvBnBiasAtenPass in conversion pipeline for integration tests. The pass enables QAT support for models containing biasless convolutions in integration tests.

Test plan

Covered by NXP internal tests.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18904

• 📄 Preview Python docs built from this PR

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

❌ 1 Awaiting Approval, 3 New Failures, 2 Unrelated Failures

As of commit f490656 with merge base 37b12c8 ():

AWAITING APPROVAL - The following workflow needs approval before CI can run:

• periodic (gh)

NEW FAILURES - The following jobs have failed:

• Copilot code review / Cleanup artifacts (gh)
  Process completed with exit code 1.
• Test CoreML Backend / test-coreml / test-backend-macos (coreml, models) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test CoreML Backend / test-coreml / test-backend-macos (coreml, operators) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

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

• pull / unittest / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / windows / windows-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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

[Copilot]

Pull request overview

Adds an ATen-graph transform into the NXP integration-test quantization flow to better support QAT graphs that include biasless convolutions (by ensuring fused/introduced conv biases are quantized/dequantized appropriately before lowering).

Changes:

• Import QuantizeFusedConvBnBiasAtenPass into the NXP integration-test utilities.
• Invoke QuantizeFusedConvBnBiasAtenPass(default_zero_bias=True) after convert_pt2e(...) when use_qat is enabled.

---

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

[Copilot]

In the NXP quantization helper (backends/nxp/quantizer/utils.py), QuantizeFusedConvBnBiasAtenPass(default_zero_bias=True) is applied unconditionally after convert_pt2e (PTQ and QAT). Gating it behind use_qat here makes the integration-test conversion pipeline diverge from the main quantization path; consider applying it unconditionally as well, or add a short comment explaining why PTQ should skip it in this pipeline.

Suggested change

	if use_qat:
	exir_program_aten_quant = QuantizeFusedConvBnBiasAtenPass(
	default_zero_bias=True
	)(exir_program_aten_quant).graph_module
	exir_program_aten_quant = QuantizeFusedConvBnBiasAtenPass(
	default_zero_bias=True
	)(exir_program_aten_quant).graph_module

[Copilot]

The chained pass invocation is likely to be reformatted by the repo’s UFMT/black (line-length wrapping tends to split at the outer callable invocation rather than inside the pass constructor). Please run UFMT/black on this file or adjust the wrapping so formatting CI doesn’t fail.

Suggested change

	)(exir_program_aten_quant).graph_module
	)(
	exir_program_aten_quant
	).graph_module