Update app.py

app.py

@@ -1,5 +1,5 @@
 # LoRA Inference Gradio Space Demo
-
+import spaces
 import gradio as gr
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -20,6 +20,7 @@ model = PeftModel.from_pretrained(
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit")
 
+@spaces.GPU
 def generate_response(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(**inputs, max_new_tokens=50)