[ET Device Support] make device support config method-based

[Gasoonjia]

Stack from ghstack (oldest at bottom):

• [ET Device Support] CUDA-native Qwen 3.5 MoE inference with device tensor pipeline #18788
• [ET Device Support] Extract shared device test utilities to reduce redundancy #18762
• [ET Device Support] Add device tensor helper functions to TensorPtr API #19828
• -> [ET Device Support] make device support config method-based #19582
• [ET Device Support] Add ExecutorchBackendConfig flags for skipping H2D/D2H copies #18760
• [ET Device Support] PropagateDevicePass inserts H2D/D2H copy ops at delegate boundaries #18730
• [ET Device Support] Define et_copy runtime h2d and d2h copy ops #18729
• [ET Device Support] Add device tensor helper functions to TensorPtr API #18761

Device memory planning and H2D/D2H copy configuration were previously global
flags on ExecutorchBackendConfig, applied uniformly across all methods in a
multi-method program. This made it impossible to configure different behaviors
per method — e.g., skipping H2D copies for one method while keeping them for
another.

This diff makes these configs method-based by:

1. Moving enable_non_cpu_memory_planning into MemoryPlanningPass, which
   already supports per-method dispatch via Dict[str, PassType] on
   ExecutorchBackendConfig.memory_planning_pass, follow other memory-planing-related config like alloc_input or alloc_output

2. Introducing PropagateDeviceConfig dataclass that groups
   skip_h2d_for_method_inputs and skip_d2h_for_method_outputs, with each
   field accepting either a single bool or a Dict[str, bool] for per-method
   overrides. A new propagate_device_config field on ExecutorchBackendConfig
   similarly accepts either a single config or Dict[str, PropagateDeviceConfig].

Differential Revision: D101243687

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19582

• 📄 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:

• /easycla is not responding

❌ 8 New Failures, 3 Unrelated Failures, 1 Unclassified Failure

As of commit 0c82961 with merge base 77df9b7 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner (gh)
• Lint / lintrunner-mypy (gh)
• pull / android / build-android (gh)
  Process completed with exit code 9.
• pull / test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 58493b6da2334f28e40429228361c9e5ff219ab12991e3673e249cf2289227e7 /exec failed with exit code 1
• pull / unittest / linux / linux-job (gh)
  exir/emit/test/test_emit.py::TestEmit::test_delegate_deduplicate
• pull / unittest / windows / windows-job (gh)
  exir/emit/test/test_emit.py::TestEmit::test_delegate_deduplicate
• pull / unittest-editable / linux / linux-job (gh)
  exir/emit/test/test_emit.py::TestEmit::test_delegate_deduplicate
• pull / unittest-editable / windows / windows-job (gh)
  exir/emit/test/test_emit.py::TestEmit::test_delegate_deduplicate

UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:

• Check Labels / Check labels (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  RuntimeError: GraphQL query

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

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

• pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh) (trunk failure)
  test_llama_stories_110m
• pull / unittest / macos / macos-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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

[JacobSzwejbka]

Review automatically exported from Phabricator review in Meta.