skip h2d and d2h copies between forward functions in gemma4-31b

[Gasoonjia]

Summary: This diff updates gemma4-31b export and runtime pipeline to skip the h2d and d2h copies between prefill and decode, and between previous round next round of decode as well.

Differential Revision: D108661628

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20286

• 📄 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, 5 Pending, 2 Unrelated Failures

As of commit aefe4cb with merge base 78e0384 ():

NEW FAILURES - The following jobs have failed:

• pull / test-sqnr-static-llm-qnn-linux (smollm2_135m) / linux-job (gh)
  RuntimeError: Command docker exec -t d70ab08ed41ed3eed42c8c2419a15735f4009f809f4f2a3f2c0083ab66b8dec2 /exec failed with exit code 92
• pull / unittest-editable / linux / linux-job (gh)
  examples/models/test/test_export.py::ExportTest::test_efficient_sam_export_to_executorch

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• MLX / test-mlx-stories110m / test-mlx-stories110m (gh) (detected as infra flaky with no log or failing log classifier)
• MLX / test-mlx-voxtral-realtime / test-mlx-voxtral-realtime (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]

@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating Diff in D108661628.

[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.