[MLX] Add aten.bitwise_or op handler#19869
Conversation
Add MLX delegate support for aten.bitwise_or Tensor and Scalar overloads, following the existing bitwise_and path through the FlatBuffer schema, Python op handler, C++ interpreter, and tests. Fixes pytorch#18926.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19869
Note: Links to docs will display an error until the docs builds have been completed. ❗ 2 Active SEVsThere are 2 currently active SEVs. If your PR is affected, please view them below:
|
@pytorchbot label "release notes: apple" |
Summary:
aten.bitwise_orTensor and Scalar overloads.bitwise_orin the runtime interpreter.Fixes #18926.
Testing:
cmake --build cmake-out-mlx --target op_test_runner -j2PATH="$PWD/.venv-mlx/bin:$PATH" .venv-mlx/bin/python -m executorch.backends.mlx.test.run_all_tests bitwise_or_bool bitwise_or_int bitwise_or_scalar --timeout 180cmake --build cmake-out-mlx --target strict_compile_test -j2git diff --checkpy_compileon changed Python fileslintrunner --take FLAKE8,CLANGFORMAT,NEWLINE,ETCAPITAL,LICENSELINTon touched files