rebase main and fix

Signed-off-by: zzhx1 <zzh_201018@outlook.com>

Author: zzhx1

tests/ut/quantization/test_w4a8_dynamic.py

@@ -11,10 +11,16 @@
 class TestAscendW4A8DynamicLinearMethod(TestBase):
 
     def setUp(self):
-        with patch('vllm_ascend.quantization.w4a8_dynamic.get_current_vllm_config') as mock_get_current_vllm_config:
+        with patch(
+                'vllm_ascend.quantization.w4a8_dynamic.get_current_vllm_config'
+        ) as mock_get_current_vllm_config:
             mock_vllm_config = Mock()
-            mock_vllm_config.quant_config = Mock(quant_description={"group_size": 256})
-            mock_vllm_config.scheduler_config = Mock(max_num_batched_tokens=2048, max_model_len=2048, enable_chunked_prefill=False)
+            mock_vllm_config.quant_config = Mock(
+                quant_description={"group_size": 256})
+            mock_vllm_config.scheduler_config = Mock(
+                max_num_batched_tokens=2048,
+                max_model_len=2048,
+                enable_chunked_prefill=False)
             mock_get_current_vllm_config.return_value = mock_vllm_config
             self.method = AscendW4A8DynamicLinearMethod()
             self.method.group_size = 8

tests/ut/torchair/models/test_torchair_deepseek_v2.py

@@ -104,7 +104,7 @@ def mock_distributed():
     mlp_tp_group.rank_in_group = 0
     mlp_tp_group.world_size = 1
     mlp_tp_group.all_gather = Mock(return_value=torch.randn(2, 4, 128))
-    
+
     mock_vllm_config = Mock()
     mock_vllm_config.scheduler_config = Mock(max_num_seqs=256)
     mock_vllm_config.model_config = Mock(max_model_len=2048, quant_config=None)