Gate FuseQATConvBN behind is_qat=True; opt in from QAT deployments

[ethansfng]

Summary:
The FuseQATConvBN pass added in D104497938 ran unconditionally inside apply_pre_edge_transform_passes. Its _prep_conv_biases step delegates to the shared _quantize_fused_conv_bias helper, which iterates every conv in the graph and asserts each conv input is dequantize_per_tensor — an invariant that only holds inside the conv-BN simulation chain prepare_qat_pt2e inserts. PTQ graphs trip the assert (T271158088).

Two failure modes seen in the wild:

• test_quantized_w8a32_conv1d_out_2 uses CadenceW8A32MixedQuantizer so activations stay float32; the conv input is the placeholder, not a dequant.
• test_conv2d_out_7 is channel_last=True, so the conv input is aten.permute, not a dequant; the helper only unwraps unsqueeze variants.

Add an is_qat: bool = False parameter to apply_pre_edge_transform_passes and only include FuseQATConvBN when True. Plumb through quantize_pt2/get_fake_quant_model and forward from the modai recipe lambda so ar_*_qat_et_recipe factories actually opt in.

QAT-trained models lowered via blobgen need a way to reach the QAT recipe. Add is_qat: bool to Packaging and have Rt700Hifi4Deployment pass train=self.packaging.is_qat to get_recipe_with_custom_settings. Models like activity_classification_artemis should set "is_qat": True in their defs.bzl packaging block.

Differential Revision: D105061752

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19601

• 📄 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:

• Run pull request jobs on OSDC runners in shadow mode

❌ 3 New Failures, 1 Unrelated Failure

As of commit 3c17a1d with merge base 7cd209d ():

NEW FAILURES - The following jobs have failed:

• pull / test-coreml-bc-macos (macos-m1-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t cdb2c66718321692376ca0c255ca2c0f04b9c5fa57b52dd8a6908b04f5e51402 /exec 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 job failed but were present on the merge base:

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

• Build Presets / apple (profiling) / build (gh) (trunk failure)

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

[meta-codesync]

@ethansfng has exported this pull request. If you are a Meta employee, you can view the originating Diff in D105061752.

[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.