Install with Helm

Helm is the primary install path for the Tensormesh Operator. A single helm install command deploys the operator, registers its CRDs (LMCacheEngine, LMCacheCoordinator, CacheBlendEngine), and by default creates an lmcache engine CR that the operator reconciles into a DaemonSet on your GPU nodes, plus a fleet coordinator the engines register with.

Prerequisites

Helm 3.8 or newer (helm version)
Cluster access with permission to create cluster-scoped resources
A reachable Kubernetes 1.28+ cluster — see Getting Started

cert-manager — the chart enables the mutating webhook by default and cert-manager issues its serving certificate:

kubectl apply -f https://github.com/cert-manager/cert-manager/releases/latest/download/cert-manager.yaml
kubectl -n cert-manager wait --for=condition=Available deploy --all --timeout=180s

Access token from the Tensormesh team

The chart is distributed through a private registry. To install it, request an access token from https://www.tensormesh.ai/contact. You’ll use it to authenticate before installing.

Quick Install

Authenticate to the registry with the token Tensormesh provided, write your configuration into my-values.yaml, and install:

my-values.yaml

engine:
  enabled: true
  spec:
    privileged: true                 # required for GPU visibility in some cluster 
    l1:
      sizeGB: 200                     # per-node L1 cache size
    image:
      repository: lmcache/vllm-openai
      tag: v0.5.3                    # pin the tag the Compatibility Matrix pairs with your chart
      pullPolicy: IfNotPresent

coordinator:
  spec:
    image:
      repository: lmcache/vllm-openai
      tag: v0.5.3                    # Same image as engine
      pullPolicy: IfNotPresent

# One-time: log in with the token Tensormesh gave you. When authenticating with a token,
# the username is not validated — any non-empty value works (we use "tensormesh" here).
echo '<TOKEN_FROM_TENSORMESH>' | helm registry login ghcr.io -u tensormesh --password-stdin

helm install tensormesh-operator \
  oci://ghcr.io/tensormesh-production/charts/tensormesh-operator \
  --version 0.5.3 \
  --namespace tensormesh-operator \
  --create-namespace \
  -f my-values.yaml \
  --wait

If install fails, jump to Troubleshooting.

Verify

The release exists

helm list -n tensormesh-operator

Example:

NAME                  NAMESPACE             REVISION  UPDATED                   STATUS    CHART                      APP VERSION
tensormesh-operator   tensormesh-operator   1         2026-08-12 02:05:00 UTC   deployed  tensormesh-operator-0.5.2  v0.5.2

STATUS should be deployed.

The operator and coordinator pods are Running

kubectl get pods -n tensormesh-operator

Example:

NAME                                              READY   STATUS    RESTARTS   AGE
tensormesh-operator-5f47f76bd6-bzmqf              1/1     Running   0          2m
tensormesh-operator-coordinator-7c6446f7c8-zc7g7  1/1     Running   0          2m

The CRD is registered

kubectl get crd | grep lmcache.ai

Example:

cacheblendengines.lmcache.lmcache.ai    2026-08-12T02:04:10Z
lmcachecoordinators.lmcache.lmcache.ai  2026-08-12T02:04:10Z
lmcacheengines.lmcache.lmcache.ai       2026-08-12T02:04:10Z

The chart ships all three CRDs (crds.enabled=true).

An engine CR exists and is being reconciled

kubectl get lmcacheengines -n tensormesh-operator

Example:

NAME                                PHASE     READY   DESIRED   AGE
tensormesh-operator-default-engine  Running   1       1         2m

The engine DaemonSet landed on your GPU nodes

# select by the engine CR's name (instance label) — the component label
# (cache-engine) also matches CacheBlend engine pods when those are enabled
kubectl get pods -n tensormesh-operator -o wide \
  -l app.kubernetes.io/instance=tensormesh-operator-default-engine

Example:

NAME                                      READY   STATUS    RESTARTS   AGE   IP            NODE
tensormesh-operator-default-engine-gfj2k  1/1     Running   0          2m    10.129.6.79   worker-gpu-a100-1

Expect one pod per GPU node. On a cluster with no GPU nodes this list is empty — which is correct, not a failure.

Run the bundled smoke tests

helm test tensormesh-operator -n tensormesh-operator

Example:

NAME: tensormesh-operator
LAST DEPLOYED: Sat May 24 02:05:00 2026
NAMESPACE: tensormesh-operator
STATUS: deployed
TEST SUITE:     tensormesh-operator-test-basic
Last Started:   2026-05-24 02:08:00 +0000 UTC
Last Completed: 2026-05-24 02:08:20 +0000 UTC
Phase:          Succeeded

Upgrade

helm upgrade tensormesh-operator \
  oci://ghcr.io/tensormesh-production/charts/tensormesh-operator \
  --version 0.5.3 -n tensormesh-operator \
  -f my-values.yaml

Roll back if needed:

helm history tensormesh-operator -n tensormesh-operator
helm rollback tensormesh-operator <revision> -n tensormesh-operator

Uninstall

helm uninstall tensormesh-operator -n tensormesh-operator

A pre-delete hook removes the chart-managed CRs (LMCacheEngine, LMCacheCoordinator, and CacheBlendEngine if enabled) first, so their finalizers run cleanly before the operator Deployment is torn down.

The CRDs survive helm uninstall — same convention cert-manager and kube-prometheus-stack use. To remove them (and cascade-delete any remaining CRs):

kubectl delete crd lmcacheengines.lmcache.lmcache.ai \
  lmcachecoordinators.lmcache.lmcache.ai \
  cacheblendengines.lmcache.lmcache.ai

Helm Values

Key	Default	What it creates
`crds.enabled`	`true`	The three CRD schemas
`operator.enabled`	`true`	The controller-manager Deployment
`engine.enabled`	`true`	An `LMCacheEngine` CR, which the operator reconciles into a DaemonSet (one cache server per GPU node)
`coordinator.enabled`	`true`	An `LMCacheCoordinator` CR — one fleet-wide Deployment the engines register with
`webhook.enabled`	`true`	The CacheBlend pod-mutating webhook. Requires cert-manager; rendering fails fast without it. The chart does not register the LMCache connection webhook — wire those pods manually
`cacheBlend.enabled`	`false`	A `CacheBlendEngine` CR — see CacheBlend. Requires `webhook.enabled=true`
`observability.enabled`	`false`	An OpenTelemetry Collector CR. Requires the OpenTelemetry Operator already installed
`openshift.enabled`	`false`	The privileged SCC binding the engine’s `hostIPC` needs — see Install on OpenShift
`tests.enabled`	`true`	The `helm test` smoke-test pods

See every value

The table above is the common subset. For the full list with defaults:

helm show values \
  oci://ghcr.io/tensormesh-production/charts/tensormesh-operator --version 0.5.3

See the Configuration reference for per-section detail and example overlays.

Next steps

vLLM Quick Start

Install, deploy vLLM against the engine, see the cache hit, run the benchmark.

Modify Existing vLLM Deployment

Patch the workload you already run to consume the engine connection ConfigMap.

Troubleshooting

Engine Pending, ImagePullBackOff, hung uninstalls, and more.

Installation

Feature List

Integrations

Management

Operator UI

Reference

Prerequisites

Quick Install

Verify

Upgrade

Uninstall

Helm Values

See every value

Next steps

vLLM Quick Start

Modify Existing vLLM Deployment

Troubleshooting

​Prerequisites

​Quick Install

​Verify

​Upgrade

​Uninstall

​Helm Values

​See every value

​Next steps

vLLM Quick Start

Modify Existing vLLM Deployment

Troubleshooting

Prerequisites

Quick Install

Verify

Upgrade

Uninstall

Helm Values

See every value

Next steps