Back to Home

Kubernetes Integration

Deploy and manage ML models on your own Kubernetes infrastructure.

Install the Operator

kubectl apply -f https://1.ml/k8s/operator.yaml

Deploy a Model

model-deployment.yaml
apiVersion: ml.1.ml/v1
kind: MLModel
metadata:
  name: my-classifier
spec:
  model: "registry.1.ml/my-model:v1"
  replicas: 3
  resources:
    gpu: "nvidia-t4"
    memory: "8Gi"
Model ServingEdge Deployment