Update app.py

app.py

@@ -55,7 +55,7 @@ def model_inference(
             ]
     prompt = processor.apply_chat_template(resulting_messages, add_generation_prompt=True)
     inputs = processor(text=prompt, images=[images], return_tensors="pt")
-    inputs = {k: v.to("cuda") for k, v in inputs.items()}
+    inputs.to("cuda", dtype=torch.bfloat16)
     generation_args = {
         "max_new_tokens": max_new_tokens,
         "repetition_penalty": repetition_penalty,