Events

This hands-on workshop guides participants through deploying a Mixtral 8X7B large language model on Google Kubernetes Engine (GKE) using Pulumi for infrastructure as code. Attendees will learn to leverage NVIDIA L4 GPUs on GKE to serve advanced AI models efficiently. The session covers setting up the Google Cloud environment, deploying a Pulumi-based GKE cluster, and containerizing the model using Hugging Face’s text generation inference.