[XPU][NPU][ROCM] enable cpu_offloading flag for non_cuda (#1488)

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>

tests/e2e/offline_inference/test_diffusion_cpu_offload.py

@@ -48,7 +48,6 @@ def inference(model_name: str, offload: bool = True):
 @pytest.mark.core_model
 @pytest.mark.diffusion
 @hardware_test(res={"cuda": "L4", "rocm": "MI325"})
-@pytest.mark.skipif(current_omni_platform.is_npu() or current_omni_platform.is_rocm(), reason="Hardware not supported")
 @pytest.mark.parametrize("model_name", models)
 def test_cpu_offload_diffusion_model(model_name: str):
     try: