Getting Started with Running Distributed Pytorch Models on Snowflake

Overview

This solution generates upsell and cross-sell recommendations to increase sales for the Tasty Bytes business. This involves:

• Extracting features from customer, menu, and purchase history.
• Preprocessing data using the Snowpark ML library.
• Training a PyTorch DLRM model with distributed processing on GPUs.
• Registering the model and deploying it to a container runtime environment.
• Running predictions and visualizing recommendations on Streamlit.
• Displaying personalized menu item recommendations along with purchase history in a Streamlit app.

Step-By-Step Guide

For prerequisites, environment setup, step-by-step guide and instructions, please refer to the QuickStart Guide.