Stream = true in llvm

utility.py

@@ -582,7 +582,7 @@ def lvlm_inference_with_ollama(conversation, max_tokens: int = 200, temperature:
     stream = chat(
         model="llava-1.5-7b-hf",
         messages= conversation,
-        stream=False,
+        stream=True,
         temperature=temperature,
         max_tokens=max_tokens,
         top_p=top_p,