Update app.py

app.py

@@ -34,6 +34,5 @@ async def generate(request: Request):
     )
 
     generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    cache[prompt] = generated_text
 
-    return {"output": generated_text, "cached": False}
+    return {"output": generated_text}