Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getlilac.com/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks through installing the Lilac GPU operator in your cluster. The operator is deployed via a Helm chart hosted on AWS ECR.

​
Prerequisites

  • Kubernetes 1.28+ — if you’re running a single node and aren’t already in a Kubernetes cluster, k3s is a lightweight option that’s easier to set up and connect
  • kubectl configured with cluster admin access
  • helm v3
  • NVIDIA GPU nodes with the NVIDIA GPU Operator installed
  • A Lilac supplier API key (generated during onboarding)

​
Install with Helm

1

Create the namespace

kubectl create namespace lilac-system
2

Install the operator

helm install lilac-gpu-operator \
  oci://public.ecr.aws/lilac/lilac-gpu-operator \
  --version 0.3.3 \
  --namespace lilac-system \
  --set apiKey="YOUR_SUPPLIER_API_KEY" \
  --set clusterName="my-gpu-cluster"
If you hit AWS Public ECR rate limits while installing or pulling the operator image, use our Docker Hub mirror instead. Keep the same command and values, but replace oci://public.ecr.aws/lilac/lilac-gpu-operator with oci://docker.io/getlilac/lilac-gpu-operator.
Replace my-gpu-cluster with a name that identifies this cluster in your dashboard.
The Helm chart automatically creates the API key secret, control plane config, CRDs, RBAC, and service accounts. No manual setup required.
3

Verify the installation

kubectl get pods -n lilac-system
You should see the operator pod running:
NAME                                              READY   STATUS    RESTARTS   AGE
lilac-gpu-operator-...                             1/1     Running   0          30s
4

Create a GPU pool

Apply a basic GPUPool to tell the operator which GPUs to manage. Save the following as gpu-pool.yaml and apply it:
apiVersion: gpu.getlilac.com/v1alpha1
kind: GPUPool
metadata:
  name: b200-gpu-pool
  namespace: lilac-system
spec:
  nodeSelector:
    nvidia.com/gpu.product: B200
  cache:
    enabled: true
    capacity: 1000Gi
  workloads:
    inference: true

kubectl apply -f gpu-pool.yaml
See GPU Pool Configuration for more advanced setups, including time-based schedules, preemption policies, per-node cache overrides, and Hugging Face token configuration.

​
Verify Control Plane Connection

Check the operator logs to confirm it connected to the Lilac control plane: 
kubectl logs -n lilac-system deploy/lilac-gpu-operator
Look for a log line like: 
INFO  control plane sync successful  cluster_id=abc123
Your cluster should also appear as Connected in the Lilac dashboard within 30 seconds.

​
Helm Values

ValueRequiredDefaultDescription
apiKeyYes—Supplier API key from the Lilac dashboard
clusterNameYes—Human-readable name for your cluster
controlPlaneUrlNohttps://api.getlilac.comControl plane URL
disconnectTimeoutNo10mTime before cluster is marked disconnected
image.tagNoChart app versionOverride the operator image tag
resources.limitsNocpu: 500m, memory: 128MiResource limits for the operator pod
resources.requestsNocpu: 10m, memory: 64MiResource requests for the operator pod

​
Upgrading

helm upgrade lilac-gpu-operator \
  oci://public.ecr.aws/lilac/lilac-gpu-operator \
  --version 0.3.3 \
  --namespace lilac-system \
  --set apiKey="YOUR_SUPPLIER_API_KEY" \
  --set clusterName="my-gpu-cluster"

​
Uninstalling

helm uninstall lilac-gpu-operator --namespace lilac-system
Uninstalling the operator will drain all Lilac inference workloads from your cluster. Your own workloads are not affected.

​
Next Steps

Configure GPU Pools

Define which GPUs Lilac can use and when.

How the Operator Works

Understand the sync loop and architecture.