run _select_moe_comm_method only in MoE model

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

Author: realliujiaxu

tests/ut/worker/test_model_runner_v1.py

@@ -68,6 +68,8 @@ def test_select_moe_comm_method(soc_version, enable_expert_parallel,
     with patch('vllm_ascend.worker.model_runner_v1.get_ascend_soc_version',
                return_value=soc_version), \
          patch('vllm_ascend.worker.model_runner_v1.is_global_first_rank',
+               return_value=True), \
+         patch('vllm_ascend.worker.model_runner_v1.is_moe_model',
                return_value=True):
 
         # Bind the real method to the mock object
@@ -102,6 +104,8 @@ def test_select_moe_comm_method_unsupported_soc():
                return_value=unsupported_soc), \
          patch('vllm_ascend.worker.model_runner_v1.is_global_first_rank',
                return_value=True), \
+         patch('vllm_ascend.worker.model_runner_v1.is_moe_model',
+                  return_value=True), \
          pytest.raises(ValueError, match=f"Unsupported soc_version: {unsupported_soc}"):
 
         NPUModelRunner._select_moe_comm_method(mock_runner, 100, False)

vllm_ascend/ops/moe/moe_comm_method.py

@@ -39,7 +39,7 @@
 
 def get_moe_comm_method(
         moe_comm_type: Optional[MoECommType]) -> Optional[MoECommMethod]:
-    return _MoECommMethods.get(moe_comm_type)
+    return _MoECommMethods.get(moe_comm_type, None)
 
 
 def setup_moe_comm_method(moe_config):

vllm_ascend/worker/model_runner_v1.py

@@ -1841,7 +1841,7 @@ def _pool(
         )
 
     def _select_moe_comm_method(self, num_tokens: int,
-                                with_prefill: bool) -> MoECommType:
+                                with_prefill: bool) -> Optional[MoECommType]:
         """1. If expert parallel is not enabled, we use all-gather since MC2 and all-to-all
         are designed for expert parallelism.
         2. If expert parallel is enabled, we need to consider the soc version and the
@@ -1864,6 +1864,9 @@ def _select_moe_comm_method(self, num_tokens: int,
         Returns:
             MoECommType: The selected MoE communication method.
         """
+        if not is_moe_model(self.vllm_config):
+            return None
+
         soc_version = get_ascend_soc_version()
         quant_type = getattr(self.vllm_config.model_config.hf_config,
                              'moe_quantize', None)