diff --git a/tests/e2e/singlecard/test_aclgraph_accuracy.py b/tests/e2e/singlecard/test_aclgraph_accuracy.py
index 0e37a6d8..948338f1 100644
--- a/tests/e2e/singlecard/test_aclgraph_accuracy.py
+++ b/tests/e2e/singlecard/test_aclgraph_accuracy.py
@@ -36,10 +36,10 @@ CASE_DS_ACLGRAPH = LLMTestCase(
     quantization="ascend",
     prompts=PROMPTS_SHORT,
     golden_answers=[
-        '\nI am a 20 year old student from the UK. I am currently studying for a degree in English Literature and Creative Writing. I have a passion',
+        '\nI am a 20 year old female, and I have been suffering from depression for 3 years now. I have been on medication for 2',
         ' a man who has been in the public eye for decades. He has been a senator, a governor, and a businessman. He has also been married to the',
         ' Paris, which is also the largest city in the country. The city is located on the River Seine and is known for its beautiful architecture, museums, and art',
-        ' here.\nThe future of AI is here.\nThe future of AI is here.\nThe future of AI is here.\nThe future of AI is'
+        ' here, and it’s not what you think.\nThe future of AI is here, and it’s not what you think.\nThe future of'
     ],
 )
 
diff --git a/tests/ut/ops/test_token_dispatcher.py b/tests/ut/ops/test_token_dispatcher.py
index d27da5cf..ff9e3cc1 100644
--- a/tests/ut/ops/test_token_dispatcher.py
+++ b/tests/ut/ops/test_token_dispatcher.py
@@ -164,11 +164,11 @@ class TestTokenDispatcherWithAllGather(TestBase):
         self.dispatcher = TokenDispatcherWithAllGather(**kwargs)
 
         # Mock NPU functions
-        self.patcher_npu_moe_init_routing_v2 = patch(
-            'torch_npu.npu_moe_init_routing_v2')
-        self.mock_npu_moe_init_routing_v2 = self.patcher_npu_moe_init_routing_v2.start(
+        self.patcher_npu_moe_init_routing_custom = patch(
+            'torch.ops._C_ascend.npu_moe_init_routing_custom')
+        self.mock_npu_moe_init_routing_custom = self.patcher_npu_moe_init_routing_custom.start(
         )
-        self.mock_npu_moe_init_routing_v2.return_value = (
+        self.mock_npu_moe_init_routing_custom.return_value = (
             torch.randn(6, 128),  # sorted_hidden_states
             torch.tensor([0, 1, 2, 3, 4, 5]),  # expanded_row_idx
             torch.tensor([0, 1, 0, 1, 0, 1]),  # expanded_expert_idx
@@ -180,7 +180,7 @@ class TestTokenDispatcherWithAllGather(TestBase):
         self.mock_npu_moe_token_unpermute.return_value = torch.randn(6, 128)
 
     def tearDown(self):
-        self.patcher_npu_moe_init_routing_v2.stop()
+        self.patcher_npu_moe_init_routing_custom.stop()
         self.patcher_npu_moe_token_unpermute.stop()
 
     def test_token_dispatch_without_expert_map(self):
@@ -192,8 +192,8 @@ class TestTokenDispatcherWithAllGather(TestBase):
                                                  topk_ids, None)
 
         # Verify npu_moe_init_routing is called
-        self.mock_npu_moe_init_routing_v2.assert_called_once()
-        args, kwargs = self.mock_npu_moe_init_routing_v2.call_args
+        self.mock_npu_moe_init_routing_custom.assert_called_once()
+        args, kwargs = self.mock_npu_moe_init_routing_custom.call_args
 
         self.assertEqual(results.group_list_type, 1)
 
@@ -207,8 +207,8 @@ class TestTokenDispatcherWithAllGather(TestBase):
                                                  topk_ids, None)
 
         # Verify npu_moe_init_routing is called
-        self.mock_npu_moe_init_routing_v2.assert_called_once()
-        args, kwargs = self.mock_npu_moe_init_routing_v2.call_args
+        self.mock_npu_moe_init_routing_custom.assert_called_once()
+        args, kwargs = self.mock_npu_moe_init_routing_custom.call_args
 
         self.assertEqual(results.group_list_type, 1)
 
@@ -366,11 +366,11 @@ class TestTokenDispatcherWithAll2AllV(TestBase):
         self.mock_npu_dynamic_quant.return_value = (torch.randn(16, 16),
                                                     torch.randn(16))
 
-        # Mock torch_npu.npu_moe_init_routing_v2
-        patcher11 = patch('torch_npu.npu_moe_init_routing_v2')
-        self.mock_npu_moe_init_routing_v2 = patcher11.start()
+        # Mock torch.ops._C_ascend.npu_moe_init_routing_custom
+        patcher11 = patch('torch.ops._C_ascend.npu_moe_init_routing_custom')
+        self.mock_npu_moe_init_routing_custom = patcher11.start()
         self.addCleanup(patcher11.stop)
-        self.mock_npu_moe_init_routing_v2.return_value = (torch.randn(
+        self.mock_npu_moe_init_routing_custom.return_value = (torch.randn(
             16, 16), torch.arange(16), None, torch.randn(16))
 
         # Mock torch.repeat_interleave
diff --git a/vllm_ascend/ops/fused_moe/token_dispatcher.py b/vllm_ascend/ops/fused_moe/token_dispatcher.py
index b40a0583..d90f4c71 100644
--- a/vllm_ascend/ops/fused_moe/token_dispatcher.py
+++ b/vllm_ascend/ops/fused_moe/token_dispatcher.py
@@ -354,7 +354,7 @@ class TokenDispatcherWithAllGather(MoETokenDispatcher):
             global_num_experts = self.num_experts_local
 
         sorted_hidden_states, expanded_row_idx, expert_tokens, pertoken_scale = (
-            torch_npu.npu_moe_init_routing_v2(
+            torch.ops._C_ascend.npu_moe_init_routing_custom(
                 hidden_states,
                 topk_ids,
                 scale=pertoken_scale,