Update app.py

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 import streamlit as st
 from time import time
 from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers.cache_utils import DynamicCache
 
 def generate(model, input_ids, past_key_values, max_new_tokens=50):
     """Token-by-token generation using cache for speed."""