DevOps & Infrastructure

GKE Inference

The Gke Inference skill deploys and optimizes AI/ML inference workloads on Google Kubernetes Engine, leveraging GPUs, TPUs, and model servers to deliver high‑performance inference. It enables teams building inference servers or deploying large language models on GKE to scale efficiently and maximize resource utilization. The skill is tailored for real‑time inference scenarios and does not support migration of existing AI workloads, GKE RAG with Cloud SQL/AlloyDB, or batch/HPC use cases.

Publisher / source

Google Skills (Verified)

Upstream record

google/skills

Version

Version 6

Published

2026-06-23

Publication review

Approved for publication

Content fingerprint

2153b93588c895ef51e972036dac35b4ef1687e663ab52d3ca3e57ce16759418