enable unidiffuser test cases on xpu (#11444)

* enable unidiffuser cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* fix a typo
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

tests/pipelines/test_pipelines_common.py

@@ -1485,8 +1485,8 @@ class PipelineTesterMixin:
         model_devices = [component.device.type for component in components.values() if hasattr(component, "device")]
         self.assertTrue(all(device == torch_device for device in model_devices))
 
-        output_cuda = pipe(**self.get_dummy_inputs(torch_device))[0]
-        self.assertTrue(np.isnan(to_np(output_cuda)).sum() == 0)
+        output_device = pipe(**self.get_dummy_inputs(torch_device))[0]
+        self.assertTrue(np.isnan(to_np(output_device)).sum() == 0)
 
     def test_to_dtype(self):
         components = self.get_dummy_components()
@@ -1677,11 +1677,11 @@ class PipelineTesterMixin:
 
         pipe.set_progress_bar_config(disable=None)
 
-        pipe.enable_model_cpu_offload(device=torch_device)
+        pipe.enable_model_cpu_offload()
         inputs = self.get_dummy_inputs(generator_device)
         output_with_offload = pipe(**inputs)[0]
 
-        pipe.enable_model_cpu_offload(device=torch_device)
+        pipe.enable_model_cpu_offload()
         inputs = self.get_dummy_inputs(generator_device)
         output_with_offload_twice = pipe(**inputs)[0]
 
@@ -2226,7 +2226,7 @@ class PipelineTesterMixin:
 
         def enable_group_offload_on_component(pipe, group_offloading_kwargs):
             # We intentionally don't test VAE's here. This is because some tests enable tiling on the VAE. If
-            # tiling is enabled and a forward pass is run, when cuda streams are used, the execution order of
+            # tiling is enabled and a forward pass is run, when accelerator streams are used, the execution order of
             # the layers is not traced correctly. This causes errors. For apply group offloading to VAE, a
             # warmup forward pass (even with dummy small inputs) is recommended.
             for component_name in [

tests/pipelines/unidiffuser/test_unidiffuser.py

@@ -22,13 +22,13 @@ from diffusers import (
     UniDiffuserTextDecoder,
 )
 from diffusers.utils.testing_utils import (
+    backend_empty_cache,
     enable_full_determinism,
     floats_tensor,
     load_image,
     nightly,
     require_torch_2,
     require_torch_accelerator,
-    require_torch_gpu,
     run_test_in_subprocess,
     torch_device,
 )
@@ -577,24 +577,24 @@ class UniDiffuserPipelineFastTests(
         assert text[0][: len(expected_text_prefix)] == expected_text_prefix
 
     @unittest.skip(
-        "Test not supported becauseit has a bunch of direct configs at init and also, this pipeline isn't used that much now."
+        "Test not supported because it has a bunch of direct configs at init and also, this pipeline isn't used that much now."
     )
     def test_encode_prompt_works_in_isolation():
         pass
 
 
 @nightly
-@require_torch_gpu
+@require_torch_accelerator
 class UniDiffuserPipelineSlowTests(unittest.TestCase):
     def setUp(self):
         super().setUp()
         gc.collect()
-        torch.cuda.empty_cache()
+        backend_empty_cache(torch_device)
 
     def tearDown(self):
         super().tearDown()
         gc.collect()
-        torch.cuda.empty_cache()
+        backend_empty_cache(torch_device)
 
     def get_inputs(self, device, seed=0, generate_latents=False):
         generator = torch.manual_seed(seed)
@@ -705,17 +705,17 @@ class UniDiffuserPipelineSlowTests(unittest.TestCase):
 
 
 @nightly
-@require_torch_gpu
+@require_torch_accelerator
 class UniDiffuserPipelineNightlyTests(unittest.TestCase):
     def setUp(self):
         super().setUp()
         gc.collect()
-        torch.cuda.empty_cache()
+        backend_empty_cache(torch_device)
 
     def tearDown(self):
         super().tearDown()
         gc.collect()
-        torch.cuda.empty_cache()
+        backend_empty_cache(torch_device)
 
     def get_inputs(self, device, seed=0, generate_latents=False):
         generator = torch.manual_seed(seed)