[Model] Molmo vLLM Integration (#9016)

Co-authored-by: sanghol <sanghol@allenai.org>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

vllm/entrypoints/chat_utils.py

@@ -163,6 +163,8 @@ class BaseMultiModalItemTracker(ABC, Generic[_T]):
                 return "<|image|>"
             if model_type == "qwen2_vl":
                 return "<|vision_start|><|image_pad|><|vision_end|>"
+            if model_type == "molmo":
+                return ""
 
             raise TypeError(f"Unknown model type: {model_type}")
         elif modality == "audio":