Add ONNX export support for baseline TRT benchmarking

[larryliu0820]

Summary:
Add --onnx flag to export.py that also exports models to ONNX format
alongside the standard .pte export. This enables baseline TRT benchmarking
via the benchmark binary which can compile and benchmark ONNX models
directly using TensorRT's native ONNX parser.

The ONNX export uses torch.onnx.export() which is built into PyTorch,
so no additional dependencies are needed.

Differential Revision: D94703568

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17771

• 📄 Preview Python docs built from this PR

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

❌ 7 New Failures, 2 Unrelated Failures

As of commit c08953c with merge base 9f2f005 ():

NEW FAILURES - The following jobs have failed:

• pull / unittest / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_linear_model
• Test TensorRT Backend / check-all-tensorrt-tests (gh)
  ERROR: TensorRT build test failed!
• Test TensorRT Backend / test-export / linux-job (gh)
  RuntimeError: Command docker exec -t 45bf72b3ebae95cc65b18baf89dd6ee5e2520d964f4465091d50b74a0b34aa12 /exec failed with exit code 4
• Test TensorRT Backend / test-models-tensorrt-cpp (add) / linux-job (gh)
  RuntimeError: Command docker exec -t 691d6752adf34fa34ed7c5245b879efac758c435a74852790650aeda71825593 /exec failed with exit code 1
• Test TensorRT Backend / test-models-tensorrt-cpp (linear) / linux-job (gh)
  RuntimeError: Command docker exec -t 45b3a208d2a0ed6765c6d8c79e170b37aef7ff4eac7e35678f141503541e39b2 /exec failed with exit code 1
• Test TensorRT Backend / test-models-tensorrt-cpp (mul) / linux-job (gh)
  RuntimeError: Command docker exec -t 07dd4f7900e0bd82f79e1f9e1afd9dd2246b043aaaa2ccba9f2e107619315961 /exec failed with exit code 1
• Test TensorRT Backend / test-tensorrt-build / linux-job (gh)
  RuntimeError: Command docker exec -t f26cfc11d39a442c61a530ef9d040f76c96c5eeb27f8ad7801e6b56e0f952deb /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

• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job (gh) (trunk failure)
  Process completed with exit code 1.
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / windows-job (gh) (trunk failure)
  Process completed with exit code 1.

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

[meta-codesync]

@larryliu0820 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D94703568.

[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.