You are an ML engineer at a retail company. You have built a machine learning model that predicts which coupon to offer an e-commerce customer at the checkout based on the items in their cart. The model is deployed using Google Cloud services. When a customer proceeds to checkout, your serving pipeline joins the customer's current cart with a row in a BigQuery table containing the customer's historic purchase behavior, and this combined data is used as the model's input to make predictions. Recently, the web development team has reported that the model's predictions are returned too slowly, causing delays in loading the coupon offer along with the rest of the web page. How should you speed up the model's prediction time to resolve this issue?