Add Arm nodes to your GKE cluster using a multi-architecture Ollama container image

Who is this for?

This Learning Path is for developers who want to compare the performance of amd64 and arm64 deployments by running inferences on a hybrid GKE cluster using an Ollama multi-architecture container image.

What will you learn?

Upon completion of this Learning Path, you will be able to:

• Create a hybrid GKE cluster with amd64 and arm64 nodes.
• Deploy Ollama services for amd64 and arm64 architectures using a single multi-architecture container image.
• Validate deployments by pinging, pulling models, and running inferences to compare architecture performance.

Prerequisites

Before starting, you will need the following:

• A Google Cloud account .
• A local machine with Google Cloud CLI and kubectl installed.
• The GKE Cloud Plugin installed.