Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 import json
 import gradio as gr
 from llama_cpp import Llama
+import spaces
 
 # Get environment variables
 model_id = os.getenv('MODEL')
@@ -34,6 +35,7 @@ llm = Llama(model_path="/home/user/.cache/huggingface/hub/models--LSX-UniWue--LL
             chat_format=chat_template)
 
 # Function for streaming chat completions
+@spaces.GPU
 def chat_stream_completion(message, history):
     #messages_prompts = [{"role": "system", "content": system_prompt}]
     messages_prompts = []