Update app.py

app.py

@@ -3,6 +3,7 @@ from transformers import AutoProcessor, AutoModelForCausalLM, GenerationConfig,
 from PIL import Image
 import gradio as gr
 from threading import Thread
+import spaces
 
 # --- 1. Model and Processor Setup ---
 # This part is loaded only once when the script starts.
@@ -45,7 +46,7 @@ except Exception as e:
     exit()
 
 # --- 2. Gradio Chatbot Logic with Streaming ---
-
+@spaces.GPU
 def process_chat_streaming(user_message, chatbot_display, messages_list, image_pil):
     """
     This generator function handles the chat logic with streaming.
@@ -173,4 +174,4 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutra
 
 
 if __name__ == "__main__":
-    demo.queue().launch(debug=True, share=True)
+    demo.launch(debug=True, mcp_server=True)