NXP backend: Refactor executorch_pipeline.py, allow different sources for calibration inputs

[roman-janik-nxp]

Summary

Introduces ModelInputSpec for specification of model inputs. Arbitrary data type of model input can now be specified. Moves creation of calibration data outside main to_quantized_edge_program() function, thus enables using different data source than random data creation.

Test plan

All tests that use executorch_pipeline.py calls - almost all of backend tests.

cc @digantdesai @JakeStevens @robert-kalmar

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13494

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• ROCm CI/CD workflows failing due to : download from https://api.github.com/repos/pytorch/pytorch timed out.

❌ 6 New Failures, 1 Unrelated Failure

As of commit eec0b4d with merge base 473df33 ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  At least one of the pre-conditions you specified did not hold
• pull / unittest / linux / linux-job (gh)
  RuntimeError: Command docker exec -t a22b05a8221323b6af32e73dacefeaf594a7d52832dbcc1d4d629992b5559605 /exec failed with exit code 3
• pull / unittest / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3
• pull / unittest-arm-backend-with-no-fvp (test_pytest_models) / linux-job (gh)
  RuntimeError: Command docker exec -t c60b1fe786e937b95a3c41fad7011e7d7e09771233a2c916e94bd7803652b7d8 /exec failed with exit code 3
• pull / unittest-arm-backend-with-no-fvp (test_pytest_ops) / linux-job (gh)
  RuntimeError: Command docker exec -t e92eb7c81bd57e28fc0a83e453b467381aefdf202425d58bb766b470043b3886 /exec failed with exit code 3
• pull / unittest-editable / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 8d81cb4ea17081de3a347dfa9947db102f78369ca72ec7b9ac7a48ce5f126459 /exec failed with exit code 3

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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

[roman-janik-nxp]

@pytorchbot label "module: nxp" "release notes: nxp"

[MartinPavella]

Test 3

[robert-kalmar]

@roman-janik-nxp Please rebase and resolve conflicts.

[shoumikhin]

@roman-janik-nxp please check the following Pyre typechecks are resolved:

    [executorch/backends/nxp/tests/executorch_pipeline.py:68:8] Incompatible return type [7]: Expected `typing.Tuple[ModelInputSpec, ...]` but got `Union[typing.Tuple[ModelInputSpec, ...], typing.Tuple[int, ...]]`.
    [executorch/backends/nxp/tests/executorch_pipeline.py:73:31] Incompatible parameter type [6]: In call `ModelInputSpec.__init__`, for 1st positional argument, expected `typing.Tuple[int, ...]` but got `typing.Tuple[Union[ModelInputSpec, int], ...]`.