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

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

vllm/model_executor/models/qwen2_5_omni_thinker.py

@@ -717,6 +717,17 @@ class Qwen2_5OmniThinkerForConditionalGeneration(
             "thinker.": "",
         })
 
+    @classmethod
+    def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
+        if modality.startswith("image"):
+            return "<|vision_start|><|IMAGE|><|vision_end|>"
+        if modality.startswith("video"):
+            return "<|vision_start|><|VIDEO|><|vision_end|>"
+        if modality.startswith("audio"):
+            return f"Audio {i}: <|audio_bos|><|AUDIO|><|audio_eos|>"
+
+        raise ValueError("Only image, video or audio modality is supported")
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super().__init__()
         thinker_config: Qwen2_5OmniThinkerConfig = (