[BugFix][Core] Fix BlockManagerV2 when Encoder Input is None (#9103)

vllm/engine/arg_utils.py

@@ -903,11 +903,6 @@ class EngineArgs:
                     "--enable-prefix-caching is currently not "
                     "supported for multimodal models and has been disabled.")
             self.enable_prefix_caching = False
-        if model_config.is_encoder_decoder_model:
-            logger.warning(
-                "Block Manager v2 does not support encoder-decoder models"
-                " currently. Using Block Manager v1 as fallback.")
-            self.use_v2_block_manager = False
 
         cache_config = CacheConfig(
             block_size=self.block_size if self.device != "neuron" else