[executorch] Rewrite remove_unused_parameters_pass for HOP support

[GregoryComer]

Stack from ghstack (oldest at bottom):

• [executorch] Update XNNPACK backend to use input_spec metadata + support HOPs #18147
• [executorch] Update delegation and partitioning to use input_spec metadata #18146
• -> [executorch] Rewrite remove_unused_parameters_pass for HOP support #18145
• [executorch] Add propagate_input_spec pass and while_loop HOP support #18144
• [executorch] Fix remove_clone_ops to prevent output aliasing #18143

Update remove_unused_parameters_pass to handle HOP submodules. Use metadata from the propagate_input_spec pass to map placeholder nodes inside control flow branches (cond, map, scan, while_loop) to top-level inputs and remove unused ones, while making sure submodule signatures match HOP call nodes.

The pass works via two sub-passes:

• First, recursively find the set of all used parameters.
• Second, recursively update HOP nodes and submodules to remove unused parameters.

Differential Revision: D95876981

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18145

• 📄 Preview Python docs built from this PR

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

❌ 23 New Failures, 1 Unrelated Failure

As of commit fdbe8cf with merge base 48bd687 ():

NEW FAILURES - The following jobs have failed:

• Build Presets / windows (pybind) / build (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Build Presets / windows (windows) / build (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
  RuntimeError: Command docker exec -t 6c7643077b84f008c6715ad7bf65928eaa6a1d3dc2118f8780c7588f4364a865 /exec failed with exit code 139
• pull / unittest / linux / linux-job (gh)
  extension/llm/modules/test/test_attention.py::AttentionTest::test_attention_torch_cond_executorch
• pull / unittest / macos / macos-job (gh)
  extension/llm/modules/test/test_attention.py::AttentionTest::test_attention_torch_cond_executorch
• pull / unittest / windows / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t e1397c39d2ea53cefa88e7bd895394317598d699b7bd1e0b631f91e534f26cac /exec failed with exit code 1
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t a6872cee4786426e3efe5a76856b5fc383d08ec65a9c6211887d560343d8e66a /exec failed with exit code 1
• pull / unittest-editable / linux / linux-job (gh)
  extension/llm/modules/test/test_attention.py::AttentionTest::test_attention_torch_cond_executorch
• pull / unittest-editable / macos / macos-job (gh)
  extension/llm/modules/test/test_attention.py::AttentionTest::test_attention_torch_cond_executorch
• pull / unittest-editable / windows / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 1ec43e8503ad3f6f06f6f3f0d6a25259a0b3477c30354e7379e7c55a942c19c6 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 88f61574787a0467787521891820a01df7f4b1f1be1cfd4feb14dab986ad4e50 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t 3653245de8c97a19d3c86478a560a9335111973133943e59a22180334db628b8 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 3d10c52be0fbe5ce6b14eb9bcb330562dd6a8898b7acfa977eb1bac45847a457 /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 02d5282f7619297f42398475f2f14c32932aded8944219e444767fdffa9b690b /exec failed with exit code 1
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t 5d06988883931059e267cb13fcd10c43d105a0a7ef51045e1a398a74084567b5 /exec failed with exit code 1
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed 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)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (nvidia, parakeet-tdt, non-quantized) / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1
• Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (nvidia, parakeet-tdt, quantized-int4-weight-only) / windows-job (gh)
  The process 'C:\Program Files\Git\cmd\git.exe' failed with exit code 1

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

• pull / test-llama_runner_eager-linux / 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.

[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.