gke-inference-quickstart
Deploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ). Covers model discovery, manifest generation, and deployment using native MCP tools and CLI.
npx skills add majiayu000/claude-skill-registry --skill gke-inference-quickstart --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# GKE Inference Quickstart (GIQ) ## Purpose This skill guides the deployment of AI/ML inference workloads on GKE using GIQ. It leverages `gcloud container ai profiles manifests create` to create optimized Kubernetes manifests based on Google's best practices and benchmarks. ## When to Use - **Goal:** Deploy an AI model (e.g., Llama, Gemma, Mistral) to GKE. - **Goal:** Generate a Kubernetes manifest for inference. - **Context:** User asks about "GIQ", "Inference Quickstart", or "AI benchmarks" on GKE. ## Prerequisites - A GKE cluster (preferably with GPU/TPU node pools, though GIQ can help identify requirements). - `gcloud` CLI installed and authenticated (for discovery commands). ## Workflow ### 1. Discovery: Find Models and Hardware Before generating a manifest, you often need to pick a valid combination of Model, Model Server, and Accelerator. **List all supported models:** ```bash gcloud container ai profiles models list ``` **Find valid accelerators and servers for a specific model:** ```bash # Replace <MODEL_NAME> with a model from the list above (e.g., 'gemma-2-9b-it') gcloud container ai profiles list --model=<MODEL_NAME> ``` **View benchmarks/profiles (optional):** To see c
- Purpose
- When to Use
- Prerequisites
- Workflow
- 1. Discovery: Find Models and Hardware
- 2. Generate Manifest
- 3. Review and Deploy
- Troubleshooting
- Reference
gcloud container ai profiles models list Replace <MODEL_NAME> with a model from the list above (e.g., 'gemma-2-9b-it') gcloud container ai profiles list --model=<MODEL_NAME> gcloud container ai profiles manifests create \ kubectl apply -f inference-workload.yaml
What does the gke-inference-quickstart skill do?
Deploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ). Covers model discovery, manifest generation, and deployment using native MCP tools and CLI.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill gke-inference-quickstart --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.