gke-inference-quickstart

Official

Deploy AI inference on GKE with GIQ.

AuthorGoogleCloudPlatform
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Deploying AI inference workloads on GKE can be complex and time-consuming due to model discovery, manifest generation, and reliable deployment orchestration. This skill streamlines the end-to-end process using Google's Inference Quickstart (GIQ) and MCP tooling to reduce setup time and errors.

Core Features & Use Cases

  • Model discovery: Identify compatible models, servers, and accelerators for your GKE deployment.
  • Manifest generation: Create optimized Kubernetes manifests with GIQ and MCP tools.
  • Deployment workflow: Validate, review, and deploy manifests to a GKE cluster, with guidance for common scenarios.

Quick Start

Tell the AI to discover your model, generate a GIQ manifest using gcloud, and deploy it to your GKE cluster.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gke-inference-quickstart
Download link: https://github.com/GoogleCloudPlatform/gke-mcp/archive/main.zip#gke-inference-quickstart

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.