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.

Migrating an existing AI inference workload to GKE v1.0.0

Use this resource to migrate an existing AI inference workload to self-hosted inference on GKE

New

  • 367 downloads
  • 132 likes
  • 112 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install gke-inference-migration-guide

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 runs a four-phase migration: discovery, solution design, implementation with gcloud and kubectl, then validation and traffic cutover. It relies on vLLM deployment, inference gateway and storage templates. You get a plan and the manifests to adapt. For a brand-new deployment with no existing workload, another skill fits better.

Mostly picked by

Updated November 2, 2026

Card for the “Migrating an existing AI inference workload to GKE” 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: discovery, design, implementation and cutover validation phases
  • assets/vllm-deployment.yaml.tmpl: vLLM deployment template
  • assets/gke-inference-gateway.yaml.tmpl: GKE inference gateway template

Good fit for

  • An inference workload on Cloud Run or the Gemini API must move to GKE
  • You want to host a model yourself on GKE with a gradual traffic cutover

Not for

    Tags

    • gke
    • inference
    • migration
    • vllm

    About

    You say

    “Migrate my Gemini inference to a model hosted on GKE, with a gradual traffic cutover.”

    Card for the “Migrating an existing AI inference workload to GKE” 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 migrate an existing AI inference workload to self-hosted inference on GKE
    3. Review and adjust the result

    Content preview

    Files

    • assets/ccc-profile.yaml.tmpl0.6 KB
    • assets/gke-inference-gateway.yaml.tmpl0.6 KB
    • assets/model-staging-job.yaml.tmpl1.6 KB
    • assets/storage-config.yaml.tmpl0.7 KB
    • assets/vllm-deployment.yaml.tmpl2 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/attribution.md2 KB
    • SKILL.md32.8 KB

    Origin and licence

    Listed unmodified

    Author
    google
    Source
    github.com/google/skills/tree/81b0e8f8f40513c31b3388e600506e8b48a85bc2/skills/cloud/google-cloud-solution-guided-gke-ai-migration
    Licence
    Apache-2.0

    Notice

    « google-cloud-solution-guided-gke-ai-migration » (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.