[Feat][Graph] Support DeepSeek with ACL Graph (#2707)

### What this PR does / why we need it?
In memory of #677 , a long overdue milestone. Now DeepSeek V3/R1 should
be OK with ACL Graph.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Working on it.

- vLLM version: v0.10.2
- vLLM main:
68dbde5dbb

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

tests/ut/models/test_deepseek_v2.py

@@ -41,9 +41,10 @@ def test_row_parallel_linear(cls, mock_distributed):
     assert output[0].shape == (2, 4, 64)
 
 
+@patch("torch.ops.vllm.mla_forward")
 @patch("torch_npu.npu_rms_norm")
-def test_custom_deepseek_v2_mla_attention(mock_rms_norm, mock_distributed,
-                                          base_config):
+def test_custom_deepseek_v2_mla_attention(mock_rms_norm, mock_mla_forward,
+                                          mock_distributed, base_config):
     mock_rms_norm.return_value = (torch.randn(2, 128), torch.randn(2, 128))
 
     attn = CustomDeepseekV2MLAAttention(config=base_config,
@@ -64,8 +65,8 @@ def test_custom_deepseek_v2_mla_attention(mock_rms_norm, mock_distributed,
     with patch.object(attn.mla_attn,
                       "__call__",
                       return_value=torch.randn(2, 4, 128)):
-        with pytest.raises(AssertionError):
-            attn(positions, x)
+        attn(positions, x)
+        mock_mla_forward.assert_called_once()
 
     attn = CustomDeepseekV2MLAAttention(config=base_config,
                                         hidden_size=128,

tests/ut/test_ascend_config.py

@@ -215,21 +215,6 @@ class TestAscendConfig(TestBase):
             test_vllm_config.model_config = fake_model_config
             init_ascend_config(test_vllm_config)
             check_ascend_config(test_vllm_config, False)
-        # aclgraph + deepseek model
-        with self.assertRaises(NotImplementedError):
-            test_vllm_config.additional_config = {
-                "torchair_graph_config": {
-                    "enabled": False,
-                },
-                "refresh": True
-            }
-            model_path = os.path.join(os.path.dirname(__file__), "fake_weight")
-            fake_model_config = ModelConfig(model=model_path)
-            fake_model_config.hf_config = PretrainedConfig()
-            fake_model_config.hf_config.model_type = "deepseek"
-            test_vllm_config.model_config = fake_model_config
-            init_ascend_config(test_vllm_config)
-            check_ascend_config(test_vllm_config, False)
 
     def test_check_torchair_supported(self):
         test_cases = [('deepseek_v3', True), ('PanguProMoE', True),