logging

app.py

@@ -56,12 +56,14 @@ def demo(image_path, prompt):
             ],
         }
     ]
-
+    print("1")
     # Preparation for inference
     text = processor.apply_chat_template(
         messages, tokenize=False, add_generation_prompt=True
     )
+    print("2")
     image_inputs, video_inputs = process_vision_info(messages)
+    print("3")
     inputs = processor(
         text=[text],
         images=image_inputs,
@@ -69,16 +71,20 @@ def demo(image_path, prompt):
         padding=True,
         return_tensors="pt",
     )
+    print("4")
     inputs = inputs.to("cuda")
-
+    print("5")
     # Inference: Generation of the output
     generated_ids = model.generate(**inputs, max_new_tokens=1500)
+    print("6")
     generated_ids_trimmed = [
         out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
     ]
+    print("7")
     output_text = processor.batch_decode(
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
     )
+    print("8")
 
     # Handle output text to convert it into JSON
     try: