GKE Inference Quickstart (GIQ)

Purpose

This skill guides the deployment of AI/ML inference workloads on GKE using GIQ. It leverages gcloud container ai profiles manifests create to create optimized Kubernetes manifests based on Google's best practices and benchmarks.

When to Use

• Goal: Deploy an AI model (e.g., Llama, Gemma, Mistral) to GKE.
• Goal: Generate a Kubernetes manifest for inference.
• Context: User asks about "GIQ", "Inference Quickstart", or "AI benchmarks" on GKE.

Prerequisites

• A GKE cluster (preferably with GPU/TPU node pools, though GIQ can help identify requirements).
• gcloud CLI installed and authenticated (for discovery commands).

Workflow