Yiming Zhou 5211f1f908 [export] Move example inputs in move_to_device_pass (#162301) ...

Summary:
If i have a EP that's exported on CPU and want to AOTI compile it for CUDA. I need to use `move_to_device_pass`.

But in `torch._inductor.aoti_compile_and_package()`, it directly uses the `example_inputs` attached to the EP, so we should move the example inputs as well if applicable.

Test Plan:
buck2 run mode/dev-nosan caffe2/test:test_export -- -r test_move_device_example_inputs

Rollback Plan:

Differential Revision: D81812366

Pull Request resolved: https://github.com/pytorch/pytorch/pull/162301
Approved by: https://github.com/angelayi

2025-09-06 23:54:54 +00:00

..

__init__.py

[export] Move example inputs in move_to_device_pass (#162301)

2025-09-06 23:54:54 +00:00