Direct Helm Chart Deployment
This page installs an Inferra LCF cluster from the tagged Cloudsmith release artifacts with Helm. It is intended for operators performing a production-style Kubernetes installation.
LCF-CLI Deployment is the recommended path: it discovers the cluster, sizes resources, and generates these values for you. Use this page when your process requires driving Helm directly.
Artifact Coordinates
Cloudsmith release publishing creates one OCI Helm chart and these OCI images.
Artifact | Coordinate | Version form |
|---|---|---|
Helm chart |
| Chart version without |
|
| Image tag with |
|
| Image tag with |
|
| Image tag with |
Bootstrap helper |
| Image tag with |
Example Release Variables:
Prerequisites
Requirement | Minimum | Notes |
|---|---|---|
Kubernetes | 1.28 | The chart declares |
Helm | 3.x | Required for OCI chart install. |
kubectl | Compatible | Assumes current kube context or |
Cloudsmith creds | Read access | Uses username |
Storage nodes | Pre-mounted XFS |
|
Inference nodes | GPU or CPU |
|
2 MiB huge pages | Recommended on inference and dual-role nodes | Backs the |
| Matching release | Used at the end to verify the deployment. |
Production Sizing Requirements
Component | Memory limit | Values set in this guide |
|---|---|---|
| Sized from selected storage; request is set equal to the limit. |
|
| Sizes the RAM tier: tier = limit − 16Gi |
|
Unlike lcft's, the lcfc limit is not a floor to clear — it is how much host RAM the KV tier gets. Raise it toward the node's memory on a dedicated node, or set it to node memory − engine budget − 16Gi where an inference engine shares the host. Step 5 of LCF-CLI Deployment covers this in full.
Step 1: Authenticate to Cloudsmith and Pull the Chart
helm registry login is rejected by an entitlement token — see the note in LCF-CLI Deployment. Write the credential into a registry configuration file of its own and pull the chart to a local file, which is what the rest of this page installs from:
The pull secret in Step 2 is built from the same file. Remove it with rm -f "$INFERRA_HELM_REGISTRY_CONFIG" when the install is finished. Your own Helm registry logins in ~/.config/helm/registry/config.json are not touched.
Step 2: Create the Namespace and Pull Secret
The secret is read from the file Step 1 wrote — the registry credential format Helm and Kubernetes share — so the token never appears on a command line.
Step 3: Label Nodes
Step 4: Prepare LCFT XFS Mount Points
mkfs.xfs -f deletes data on the selected device. Run it only on devices dedicated to LCF.
Example for one storage node:
The full multi-device procedure, including persisting the mounts in /etc/fstab, is in LCF-CLI Deployment under Step 3: Prepare XFS Mount Points.
Step 5: Prepare Helm Values
Create inferra-prod-values.yaml:
imageTag above shows ${LCF_IMAGE_TAG} for readability. Substitute the literal value (for example v1.2.0) before installing.
Step 6: Validate and Install
Both commands use the chart file pulled in Step 1, so neither re-authenticates to the registry.
On a cluster with one schedulable node, add lcf-api.replicas: 1 to inferra-prod-values.yaml. The chart requests two replicas with hard pod anti-affinity; the second can never be scheduled, and --wait will burn its whole timeout before failing the release.
Next: verify the deployment with Troubleshooting, then prove the cache works with Post-Deployment Validation.