Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Deploy AI inference on GKE with GPU or TPU v1.0.0

Use this resource to deploy a model inference server on GKE with GPUs or TPUs

New

  • 404 downloads
  • 221 likes
  • 174 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install gke-ai-inference

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent checks the models and the valid accelerator and server combinations, generates a Kubernetes manifest from Google's Inference Quickstart, reviews the values to replace (tokens, volumes) and deploys. It covers deploying models, not migrating existing AI applications or batch compute.

Mostly picked by

Updated November 2, 2026

Card for the “Deploy AI inference on GKE with GPU or TPU” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: model discovery, manifest generation and review before deployment
  • SKILL.md: prerequisites and checks for placeholders (tokens, PVCs)

Good fit for

  • You want to serve a small open-source LLM on your own GPUs
  • You must pick the GPU and server combination for a given model

Not for

    Tags

    • inference
    • GPU
    • TPU
    • LLM

    About

    You say

    “Which accelerator do I need to serve Gemma 2 9B on GKE? Generate the manifest too.”

    Card for the “Deploy AI inference on GKE with GPU or TPU” skill

    Skill published by google under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to deploy a model inference server on GKE with GPUs or TPUs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/attribution.md1.9 KB
    • SKILL.md8.4 KB

    Origin and licence

    Listed unmodified

    Author
    google
    Source
    github.com/google/skills/tree/81b0e8f8f40513c31b3388e600506e8b48a85bc2/skills/cloud/gke-inference
    Licence
    Apache-2.0

    Notice

    « gke-inference » (google, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.