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

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

vllm/model_executor/models/skyworkr1v.py

@@ -648,6 +648,13 @@ class SkyworkR1VProcessingInfo(BaseSkyworkR1VProcessingInfo):
     dummy_inputs=SkyworkR1VDummyInputsBuilder)
 class SkyworkR1VChatModel(nn.Module, SupportsMultiModal, SupportsPP):
 
+    @classmethod
+    def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
+        if modality.startswith("image"):
+            return "<image>"
+
+        raise ValueError("Only image modality is supported")
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = "") -> None:
         super().__init__()