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

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

vllm/model_executor/models/deepseek_vl2.py

@@ -315,6 +315,13 @@ class DeepseekVLV2ForCausalLM(nn.Module, SupportsMultiModal, SupportsPP):
         "language.": "language_model.",
     })
 
+    @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 = ""):
         super().__init__()
         config: DeepseekVLV2Config = vllm_config.model_config.hf_config