
Guides moving existing AI inference workloads from Cloud Run or Gemini API to GKE
- Open source
- 24.4K GitHub stars
- Cloud and infrastructure


Guides moving existing AI inference workloads from Cloud Run or Gemini API to GKE

Generates hardened, GKE-ready Kubernetes YAML manifests for Autopilot and Standard

Guides creating and auditing GKE clusters from golden-path templates for Autopilot

Diagnoses GKE TPU training throughput drops using ML Diagnostics and Cloud Monitoring

Guides an agent through GKE cluster creation, kubectl credentials and Autopilot vs

Guides configuring, tuning and debugging GKE ComputeClasses for Spot, accelerator

Guides agents through diagnosing GKE TPU multi-slice training hangs using MXLA analyzer

Guides an agent through setting up AI Runway on an existing AKS cluster for model serving

Guides an agent through running batch, HPC and job-queue workloads on GKE

Monitors GKE TPU nodes, node pools and workloads using system metrics and PromQL

Guides an agent through enabling, tuning and troubleshooting GKE Cluster Autoscaler

Diagnoses and mitigates GKE GPU and TPU node disruptions from host maintenance events
The closest alternatives to Gke inference are Google cloud solution guided gke AI migration, Gke manifest generation, Gke cluster creation, Gke AI troubleshooting tpu performance degradation and Gke basics.
Yes. Google cloud solution guided gke AI migration, Gke manifest generation, Gke cluster creation have a free or open-source option.