Fix depthwise conv detection for groups==in_channels==1

[JakeStevens]

Summary:
GitHub PR 17528 broke test_silero_vad_16k_quantized_opt3 by removing the
len(weight_shape) == 4 guard from the depthwise detection logic. This
caused regular 1D convolutions with in_channels == groups == 1 (e.g.
Silero VAD's learned STFT conv) to be misclassified as depthwise.

This diff fixes the bug and centralizes the depthwise check into a single
is_depthwise_conv(groups, in_channels) utility in utils.py that
enforces groups > 1 and groups == in_channels. All 7 depthwise
detection sites across 4 files now use this shared function:

• utils.py: Added is_depthwise_conv() — the single source of truth.
• ops_registrations.py: 4 meta functions updated (quantized_conv2d_nhwc,
  per_tensor, asym8s, asym8u).
• ref_implementations.py: Updated quantized_conv2d_nhwc_per_tensor.
• replace_ops.py: Updated ReplaceConvWithChannelLastConvPass.
• type_dispatch.py: Updated CompileTimeTypeDispatchPass (also fixed a
  pre-existing bug where groups > 1 was missing entirely).
• test_ref_implementations.py: Fixed the test harness to squeeze the
  IC=1 dim for depthwise weights when converting to channels_last format,
  matching the actual replace_ops.py pipeline behavior.
• test_replace_ops_passes.py: Added regression test for the
  in_channels==groups==1 case and a positive test for 1D depthwise.

Differential Revision: D93869048

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17590

• 📄 Preview Python docs built from this PR

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

❌ 5 New Failures, 1 Unrelated Failure

As of commit 7c3bba6 with merge base d6e8ad1 ():

NEW FAILURES - The following jobs have failed:

• pull / test-mediatek-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 19bbf6933d2ab2cb6871af2fb6699603f5196e67a903d7cd09831b85ae68df16 /exec failed with exit code 2
• pull / test-openvino-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 23849e1ae6d786cda8d3187d8d779dfee33248695db4c37e8799142fbd1e5f6d /exec failed with exit code 1
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t cf355f1ec6af76f94cdf556da48387d0f13c2d1644ebcbe08905839a453aab52 /exec failed with exit code 1
• pull / test-samsung-quantmodels-linux / linux-job (gh)
  RuntimeError: Command docker exec -t ea0ce7d08bff3b1aea4e49655839368842da8ffe951f8658d1965c4ab8614a18 /exec failed with exit code 1
• pull / unittest-buck / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 9aef6be0e3635a0030efc32d8153cd152b2dd65d85b79cfd9d4edb6e40843d2a /exec failed with exit code 3

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

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

• pull / unittest-buck / macos / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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

[meta-codesync]

@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D93869048.

[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.