Thread method-scoped kernel registry through Program and Method (#19561)

[JacobSzwejbka]

Summary:

Certain kernels might make optimizations that are broadly optimal but sub optimal for a specific model. In those scenarios it is useful to expose a backdoor for the exception method to defer to a different implementation without forcing the root imlementation to have to handle all possible dispatches.

This is just a proposal impl because things still get a little weird because ET today tends to have kernel impls get auto registered. Might need follow ups to allow generating boxed kernels separately from registering them into ETs generic kernel registry.

Reviewed By: rascani

Differential Revision: D98080033

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19561

• 📄 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:

• Run pull request jobs on OSDC runners in shadow mode

❌ 5 New Failures, 1 Cancelled Job, 4 Unrelated Failures

As of commit 0682ab2 with merge base 8e8e957 ():

NEW FAILURES - The following jobs have failed:

• Build Presets / apple (profiling) / build (gh)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (pybind) / build (gh)
• Build Presets / linux (linux, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.
• Lint / lintrunner (gh)
  Process completed with exit code 1.
• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 0a8a9f0023673f99cdf568ae0197352fa7d3f4a1fa463648b1163f4bce2bb7ea /exec failed with exit code 1

CANCELLED JOB - The following job was cancelled. Please retry:

• Test CoreML Backend / test-coreml / test-backend-macos (coreml, operators) / macos-job (gh)
  ##[error]The operation was canceled.

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

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

• Build Presets / apple (ios-simulator) / build (gh) (trunk failure)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (ios) / build (gh) (trunk failure)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (llm) / build (gh) (trunk failure)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (macos) / build (gh) (trunk failure)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?

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

[meta-codesync]

@JacobSzwejbka has exported this pull request. If you are a Meta employee, you can view the originating Diff in D98080033.

[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.