[Model] Initialize support for Deepseek-VL2 models (#11578)

Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

vllm/entrypoints/chat_utils.py

@@ -403,8 +403,8 @@ class BaseMultiModalItemTracker(ABC, Generic[_T]):
             if model_type.startswith("llava"):
                 return self._cached_token_str(self._tokenizer,
                                               hf_config.image_token_index)
-            if model_type in ("chameleon", "internvl_chat", "NVLM_D",
-                              "h2ovl_chat"):
+            if model_type in ("chameleon", "deepseek_vl_v2", "internvl_chat",
+                              "NVLM_D", "h2ovl_chat"):
                 return "<image>"
             if model_type == "mllama":
                 return "<|image|>"