[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>

examples/offline_inference_vision_language.py

@@ -300,6 +300,23 @@ def run_mllama(question: str, modality: str):
     return llm, prompt, stop_token_ids
 
 
+# Molmo
+def run_molmo(question, modality):
+    assert modality == "image"
+
+    model_name = "allenai/Molmo-7B-D-0924"
+
+    llm = LLM(
+        model=model_name,
+        trust_remote_code=True,
+        dtype="bfloat16",
+    )
+
+    prompt = question
+    stop_token_ids = None
+    return llm, prompt, stop_token_ids
+
+
 # GLM-4v
 def run_glm4v(question: str, modality: str):
     assert modality == "image"
@@ -331,6 +348,7 @@ model_example_map = {
     "qwen_vl": run_qwen_vl,
     "qwen2_vl": run_qwen2_vl,
     "mllama": run_mllama,
+    "molmo": run_molmo,
     "glm4v": run_glm4v,
 }