Improve YOCO static attention: reusable helper, correct tensor op, runtime guard (#18545)

[viveknayakatmeta]

Summary:

• replace the inline first_kv_shared index computation in _from_config with a reusable _is_kv_shared_layer() helper that matches llama_transformer.py's pattern and adds a missing first_shared <= 0 edge-case guard,
• fix torch.cat → torch.stack in _process_normal_kv for SHA kv_to_share construction, since per-head K/V tensors are rank-3 and torch.cat(dim=1) concatenates seq dimensions incorrectly while torch.stack(dim=1) correctly inserts a new heads dimension,
• change the forward() K/V skip guard from structural (if self.is_kv_shared_layer) to runtime (if shared_kv is not None) with an added assertion that self.is_kv_shared_layer holds.

Reviewed By: billmguo

Differential Revision: D97637849

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18545

• 📄 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, 2 Unrelated Failures

As of commit c81fb28 with merge base 6fccd5a ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner-mypy (gh)
  >>> Lint for backends/arm/test/models/stable_diffusion/stable_diffusion_module_test_configs.py:
• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh)
  RuntimeError: Command docker exec -t b29bf5422002802d805d4f87a720946abc7fca6a070723f897474e31ce440ad4 /exec 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.

[meta-codesync]

@viveknayakatmeta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D97637849.

[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.