[Core] Move multimodal placeholder from chat utils to model definition (#20355)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/qwen2_audio.py

@@ -251,6 +251,13 @@ class Qwen2AudioMultiModalProcessor(
 class Qwen2AudioForConditionalGeneration(nn.Module, SupportsMultiModal,
                                          SupportsPP):
 
+    @classmethod
+    def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
+        if modality.startswith("audio"):
+            return f"Audio {i}: <|audio_bos|><|AUDIO|><|audio_eos|>"
+
+        raise ValueError("Only audio modality is supported")
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super().__init__()
         config = vllm_config.model_config.hf_config