Fix quantized_w8a32_gru output shape to preserve batch dimensions

[ethansfng]

Summary:
The meta function for quantized_w8a32_gru returned shape (2, hidden_dim),
dropping the batch dimensions of the hidden state. After the fusion pass replaces
aten.gru.input with the custom op, getitem[0] on the output produced shape
(hidden_dim,) instead of the original (batch, ..., hidden_dim), causing a
shape mismatch with the reference output and NaN in the comparison.

Fix the meta function to return (2, *hidden.shape) to preserve all dimensions.
Also update the reference implementation to handle 3D hidden states and preserve
the original shape in the output, consistent with the shape fix applied to
quantized_w8a32_conv in D84745967.

Differential Revision: D92570517

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17291

• 📄 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, 1 Unrelated Failure

As of commit 09daf81 with merge base 7823792 ():

NEW FAILURES - The following jobs have failed:

• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 166d64b9b70082bd393dc6c54ee5361953741b7aa60c5f2669eb3cf1aae57048 /exec failed with exit code 1
• pull / test-samsung-quantmodels-linux / linux-job (gh)
  RuntimeError: Command docker exec -t a6408eff4bdaa1d037faea8979e1b8273142e0aefc2fec7e52bfce5378c80a7b /exec failed with exit code 1

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / test-models-linux (ic4, xnnpack-quantization-delegation, linux.4xlarge.memory) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)

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 D92570517.

[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.