transformers

fc700c2a - Fix convert_and_export_with_cache failures for GPU models (#38976)

Fix convert_and_export_with_cache failures for GPU models (#38976) * Add the `device` option for `generate()` * Add device for default tensors to avoid tensor mismatch * [test] Enable test_static_cache_exportability for torch_device * infer device from the prompt_token_ids * Add device for generated tensor * [Test] Make `test_export_static_cache` tests to run on devices rather than only CPU * fix format * infer device from the model