update

Author: a-r-r-o-w

tests/pipelines/test_pipelines_common.py

@@ -1378,25 +1378,27 @@ def test_float16_inference(self, expected_max_diff=5e-2):
         for component in pipe_fp16.components.values():
             if hasattr(component, "set_default_attn_processor"):
                 component.set_default_attn_processor()
-
         pipe_fp16.to(torch_device, torch.float16)
         pipe_fp16.set_progress_bar_config(disable=None)
 
         inputs = self.get_dummy_inputs(torch_device)
         # Reset generator in case it is used inside dummy inputs
         if "generator" in inputs:
             inputs["generator"] = self.get_generator(0)
-
-        output = pipe(**inputs)[0].cpu()
+        output = pipe(**inputs)[0]
 
         fp16_inputs = self.get_dummy_inputs(torch_device)
         # Reset generator in case it is used inside dummy inputs
         if "generator" in fp16_inputs:
             fp16_inputs["generator"] = self.get_generator(0)
+        output_fp16 = pipe_fp16(**fp16_inputs)[0]
+
+        if isinstance(output, torch.Tensor):
+            output = output.cpu()
+            output_fp16 = output_fp16.cpu()
 
-        output_fp16 = pipe_fp16(**fp16_inputs)[0].cpu()
         max_diff = numpy_cosine_similarity_distance(output.flatten(), output_fp16.flatten())
-        assert max_diff < 1e-2
+        assert max_diff < expected_max_diff
 
     @unittest.skipIf(torch_device not in ["cuda", "xpu"], reason="float16 requires CUDA or XPU")
     @require_accelerator