[VLM] Remove BaseProcessingInfo.get_mm_max_tokens_per_item (#16408)

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

vllm/model_executor/models/llava.py

@@ -137,13 +137,6 @@ class BaseLlavaProcessingInfo(BaseProcessingInfo):
     def get_supported_mm_limits(self) -> Mapping[str, Optional[int]]:
         return {"image": None}
 
-    def get_mm_max_tokens_per_item(
-        self,
-        seq_len: int,
-        mm_counts: Mapping[str, int],
-    ) -> Mapping[str, int]:
-        return {"image": self.get_max_image_tokens()}
-
     def _apply_feature_select_strategy(
         self,
         strategy: str,