All skills
google-cloud-solution-guided-gke-ai-migration
Guides migrating an existing AI inference workload to self-hosted GKE inference with gcloud and kubectl.
- Part of google/skills
- 6.1k installs
- DevOps & Self-hosting · Containers and clusters
When to use it
You already run inference on Cloud Run, the Gemini API, or a VM and need a GKE deployment plan with manifests and cutover steps.
For example
You say
Use google-cloud-solution-guided-gke-ai-migration to move my Cloud Run Llama 3 70B service to GKE on A100 GPUs.
You get
- VRAM and hardware sizing
- vLLM Deployment and Gateway manifests
- Model staging Job manifest
How it works
- Runs a four-phase flow: discovery, design, implementation, validation.
- Defaults to vLLM behind an internal Gateway with Cloud Storage FUSE staging.
- Writes progress to migration-state.md so work can resume later.
More Containers and clusters skills
See all- kubernetes-specialist14.9kCreates and manages Kubernetes workloads, manifests, Helm charts, RBAC rules and pod debugging.
- dynamo-recipe-runner2.6kSelects, validates, patches, and deploys NVIDIA Dynamo Kubernetes recipes for model serving.
- dynamo-interconnect-check1.9kValidates that a Dynamo deployment's NIXL, UCX, and NCCL interconnect is ready for disaggregated serving.
- kubernetes-architect1kPlans and reviews Kubernetes setups, including GitOps workflows and enterprise container orchestration.
Also in this pack
- cloud-run-basics19.4kDeploys and manages Cloud Run services, jobs and worker pools.
- gemini-api18.8kWrites code that calls Gemini models for text, images, video, audio, embeddings and more across languages.
- google-cloud-recipe-auth17.1kExplains how to authenticate and authorize users and services to Google Cloud APIs, including IAM and ADC.
- google-cloud-recipe-onboarding16.9kWalks a new developer through creating a Google Cloud account, setting up billing and deploying a first resource.