diff --git a/vllm_omni/model_executor/models/mimo_audio/mimo_audio.py b/vllm_omni/model_executor/models/mimo_audio/mimo_audio.py
index 162c4eb00..9528f0bfb 100644
--- a/vllm_omni/model_executor/models/mimo_audio/mimo_audio.py
+++ b/vllm_omni/model_executor/models/mimo_audio/mimo_audio.py
@@ -255,7 +255,7 @@ class MiMoAudioLLMDummyInputsBuilder(BaseDummyInputsBuilder[MiMoAudioLLMProcessi
 
         dummy_processor_inputs = ProcessorInputs(
             prompt=dummy_text,
-            mm_items=dummy_mm_items,
+            mm_data_items=dummy_mm_items,
         )
 
         return dummy_processor_inputs
@@ -309,10 +309,6 @@ class MiMoAudioDataParser(MultiModalDataParser):
         if data is None:
             return AudioProcessorItems(None)
 
-        # also check single audio item with sampling rate
-        if self._is_empty(data) or (isinstance(data, tuple) and self._is_empty(data[0])):
-            return None
-
         if (
             is_list_of(data, float)
             or isinstance(data, (np.ndarray, torch.Tensor))