Verification Checklist

View as Markdown

Pre-Deployment Checklist

Before proceeding, ensure each item passes:

1

Cluster Access

$kubectl get nodes

Shows all cluster nodes in Ready state

2

GPU Nodes Available

$kubectl get nodes -o json | jq '.items[].status.capacity."nvidia.com/gpu"'

Shows GPU count for GPU nodes

3

Helm Installed

$helm version

Shows Helm 3.x

4

Storage Available

$kubectl get storageclass

Shows at least one storage class

5

Credentials Ready

  • License key obtained
  • Container registry credentials
  • Model download URL
6

Sufficient Resources

$kubectl top nodes

Shows available resources for deployment

7

Permissions Check

$kubectl auth can-i create deployments
$kubectl auth can-i create services
$kubectl auth can-i create secrets

All return yes

Quick Verification Script

Run this script to check all prerequisites at once:

$#!/bin/bash
$echo "=== Kubernetes STT Prerequisites Check ==="
$
$echo -n "kubectl: "
$kubectl version --client &>/dev/null && echo "OK" || echo "MISSING"
$
$echo -n "Helm: "
$helm version &>/dev/null && echo "OK" || echo "MISSING"
$
$echo -n "Cluster Access: "
$kubectl cluster-info &>/dev/null && echo "OK" || echo "FAILED"
$
$echo -n "Nodes Ready: "
$kubectl get nodes | grep -q "Ready" && echo "OK" || echo "FAILED"
$
$echo -n "Storage Class: "
$kubectl get storageclass &>/dev/null && echo "OK" || echo "MISSING"
$
$echo -n "GPU Resources: "
$kubectl get nodes -o json | jq -e '.items[].status.capacity."nvidia.com/gpu"' &>/dev/null && echo "OK" || echo "NOT DETECTED"
$
$echo "=== Check Complete ==="

AWS-Specific Prerequisites

If deploying on AWS EKS, see: