Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 import gradio as gr
 from huggingface_hub import login
 from huggingface_hub import InferenceClient
+import spaces
 
 # Retrieve API key and authenticate
 api_key = os.getenv("LLAMA")
@@ -10,6 +11,7 @@ login(api_key)
 # Initialize InferenceClient for the Llama model
 client = InferenceClient("meta-llama/Llama-3.1-70B-Instruct")
 
+@spaces.GPU
 def respond(
     message,
     history: list[dict],