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

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

vllm/model_executor/models/llava_onevision.py

@@ -446,6 +446,15 @@ class LlavaOnevisionForConditionalGeneration(nn.Module, SupportsMultiModal,
             "lm_head.": "language_model.lm_head.",
         })
 
+    @classmethod
+    def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
+        if modality.startswith("image"):
+            return "<image>"
+        if modality.startswith("video"):
+            return "<video>"
+
+        raise ValueError("Only image or video modality is supported")
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = "") -> None:
         super().__init__()
         config = vllm_config.model_config.hf_config