Update app.py

app.py

@@ -1,9 +1,12 @@
 import gradio as gr
+import spaces
+
 from vllm import LLM, SamplingParams
 
 llm = LLM(model="meta-llama/Llama-2-7B-Chat-hf")
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
+@spaces.GPU
 def pipe(text: str):
     prompt = [text]
     tokens = llm.generate(prompt, sampling_params)