Fix Glm4v test (#41011)

fix

Author: Cyrilvallez

tests/models/glm4v_moe/test_modeling_glm4v_moe.py

@@ -297,6 +297,7 @@ def test_inputs_embeds_matches_input_ids(self):
 
 
 @require_torch
+@slow
 class Glm4vMoeIntegrationTest(unittest.TestCase):
     model = None
 
@@ -310,7 +311,8 @@ def get_model(cls):
 
     @classmethod
     def tearDownClass(cls):
-        del cls.model
+        if hasattr(cls, "model"):
+            del cls.model
         cleanup(torch_device, gc_collect=True)
 
     def setUp(self):
@@ -364,7 +366,6 @@ def setUp(self):
     def tearDown(self):
         cleanup(torch_device, gc_collect=True)
 
-    @slow
     def test_small_model_integration_test(self):
         inputs = self.processor.apply_chat_template(
             self.message, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt"
@@ -386,7 +387,6 @@ def test_small_model_integration_test(self):
         )
         torch.testing.assert_close(expected_pixel_slice, inputs.pixel_values[:6, :3], atol=1e-4, rtol=1e-4)
 
-    @slow
     def test_small_model_integration_test_batch(self):
         model = self.get_model()
         batch_messages = [self.message, self.message2, self.message_wo_image]
@@ -414,7 +414,6 @@ def test_small_model_integration_test_batch(self):
             EXPECTED_DECODED_TEXT,
         )
 
-    @slow
     def test_small_model_integration_test_with_video(self):
         processor = AutoProcessor.from_pretrained("zai-org/GLM-4.5V", max_image_size={"longest_edge": 50176})
         model = self.get_model()
@@ -437,7 +436,6 @@ def test_small_model_integration_test_with_video(self):
         )
 
     @run_first
-    @slow
     @require_flash_attn
     @require_torch_gpu
     def test_small_model_integration_test_batch_flashatt2(self):