DynamoComponentDeployment (DCD) Reference

Field reference for the DynamoComponentDeployment custom resource — the single Dynamo component that a DynamoGraphDeployment reconciles into pods.

View as MarkdownOpen in Claude

A DynamoComponentDeployment (DCD) describes one component of a Dynamo inference graph — a frontend, a worker, a prefill or decode worker, a planner, or an EPP. The operator reconciles each DCD into a Kubernetes Deployment (or Grove workload) plus its Services, ConfigMaps, and pods.

A DCD is rarely authored on its own. Each entry in a DynamoGraphDeployment spec.components list is a DynamoComponentDeploymentSharedSpec, the same shape documented here under Shared component spec. The operator creates one child DCD per component. Author a standalone DCD only when you want to manage a single component’s lifecycle independently; otherwise define components inside a DGD.

This page documents the nvidia.com/v1beta1 API — the served, current version.

This reference covers user-configurable spec fields. For platform installation and operator configuration, see Install Dynamo.

Minimal example

apiVersion: nvidia.com/v1beta1
kind: DynamoComponentDeployment
metadata:
name: my-worker
spec:
backendFramework: vllm
type: worker
replicas: 1
podTemplate:
spec:
containers:
- name: main
image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.4.0

Spec reference

The DCD spec is backendFramework plus the shared component spec inlined at the same level.

backendFramework
string

Inference backend framework for this component. Drives backend-specific defaults the operator injects into the main container.

Allowed values: sglang vllm trtllm

Shared component spec

These fields are shared between a standalone DCD and each entry of a DGD spec.components list, except where a field is marked DGD-only. In a DGD, prefix them with spec.components[*].

providerOverride
ProviderOverride

Customizes the primary Grove unit for a component embedded in a DGD. Standalone DCD OpenAPI omits this field. Use apiVersion: grove.io/v1alpha1; the target is PodCliqueTemplateSpec for a component backed by a PodClique or PodCliqueScalingGroupConfig for one backed by a scaling group. The value may set only topologyConstraint. See ProviderOverride.

name
stringRequired

Stable logical identifier for the component, unique within its parent DGD’s spec.components list. Must match ^[A-Za-z0-9]([-A-Za-z0-9]*[A-Za-z0-9])?$, 1–63 characters. For a standalone DCD the defaulting webhook populates name from metadata.name, so you rarely set it explicitly. The name is decoupled from the underlying workload name so the operator can rename child workloads (for example, hash-suffixing worker DCDs during a rolling update) without losing the identity that labels, status maps, scaling adapters, planner RBAC, and EPP filters depend on.

type
string

Role of the component within the graph. Drives port mapping, frontend detection, planner RBAC, and the pod label nvidia.com/dynamo-component-type. prefill and decode are first-class values for disaggregated serving and can be set directly. At most one component per graph may be epp. Immutable after it is set.

Allowed values: frontend worker prefill decode planner epp
runtimeVersionOverride
string

Declares the Dynamo runtime version in the component’s main image, taking precedence over the image tag. Use canonical MAJOR.MINOR.PATCH, for example "1.4.0", with each part between 0 and 9999 and no leading zeros, v prefix, prerelease suffix, or build metadata. This field does not change the image. See Runtime Version Compatibility for admission requirements and rollout behavior.

replicas
integer

Desired number of complete component instances. For a single-node component, each instance is one pod. For a multinode component, each instance contains all of its roles. Minimum 0. When scalingAdapter is set, this field is owned by the DynamoGraphDeploymentScalingAdapter and should not be modified directly.

minAvailable
integer

Minimum complete component replicas guaranteed to be gang-scheduled before a shortfall triggers gang termination. Supported only for Grove-backed DGD components, where it defaults to 1; rejected for non-Grove deployments. Minimum 1 and immutable after creation. Positive replicas must be at least this value. Scaling to 0 is allowed and retains minAvailable for the next scale-up.

podTemplate
core/v1.PodTemplateSpec

Pod template for the component’s pods. New components must include a container named main with a non-empty image; the operator injects command, environment, port, probe, resource, and volume-mount defaults into that container, merging your overrides by name. Existing components created without a main image may retain that omission on unrelated updates. For DGD components whose image has no parseable semantic-version tag, set runtimeVersionOverride. Every other container is treated as a user-managed sidecar and receives no injected defaults — sidecars must specify their own required fields such as image. Replaces the ten separate per-component fields (resources, envs, livenessProbe, and so on) that existed in v1alpha1.

core/v1.PodTemplateSpec
multinode
MultinodeSpec

Configures a worker, prefill, or decode component that spans multiple pods. Other component types reject this field. A pre-existing unsupported combination can remain unchanged during unrelated updates or remove multinode, but cannot change or reintroduce it. See Multinode Orchestration.

nodeCount
integerDefaults to 2

Number of nodes to deploy. Minimum 2 and immutable after creation. Total GPUs used is nodeCount × container GPU request.

roles
[]ComponentRoleSpec

Optional explicit structure of a compound component. In this release, roles are supported for multinode components and must contain exactly one leader and one worker. Omit the field to retain the implicit leader/worker layout.

name
stringRequired

Semantic role name. Multinode components allow leader and worker.

replicas
integer

Logical cardinality of the role in one complete component instance. For multinode, admission defaults and persists an omitted value as leader: 1 or worker: multinode.nodeCount - 1; an explicit value must match that fixed shape.

providerOverride
ProviderOverride

Provider configuration for the workload unit generated for this role. Available only on components embedded in a DGD; standalone DCD OpenAPI omits this field. For Grove multinode leader and worker roles, use target PodCliqueTemplateSpec; only topologyConstraint is allowed in value. Role overrides are not supported for inter-pod GMS components. See ProviderOverride.

podTemplate
core/v1.PodTemplateSpec

Reserved for role-specific pod configuration. No component type supports this field in this release; admission rejects it. Use the component-level podTemplate instead.

core/v1.PodTemplateSpec
sharedMemorySize
resource.Quantity

Size of the tmpfs mounted at /dev/shm. Omit to use the operator default (8Gi); set a positive quantity for a custom size; set "0" to disable the shared-memory volume entirely.

resource.Quantity
globalDynamoNamespace
booleanDefaults to false

Places the component in the global Dynamo namespace rather than the per-deployment namespace derived from the DGD name.

modelRef
ModelReference

References a model served by this component. When set, a headless service is created for endpoint discovery.

name
stringRequired

Base model identifier, for example llama-3-70b-instruct-v1.

revision
string

Model revision or version.

scalingAdapter
ScalingAdapter

Opts the component into a DynamoGraphDeploymentScalingAdapter (DGDSA). Set it — even as an empty object, scalingAdapter: {} — to create a DGDSA that owns replicas so external autoscalers (HPA, KEDA, Planner) can drive scaling through the Scale subresource. Omit the field to opt out.

frontendSidecar
string

Designates a container in podTemplate.spec.containers as the frontend sidecar. The value must match a container name in that list; the operator merges its frontend-sidecar defaults (Dynamo env vars, ports, health probes) into that container the same way it merges into main. The validation webhook rejects values that match no container.

compilationCache
CompilationCacheConfig

Configures a PVC-backed compilation cache. The operator handles backend-specific mount paths and environment variables, so you do not hand-wire them into podTemplate.

pvcName
stringRequired

Name of a user-created PVC, which must exist in the same namespace as the deployment.

mountPath
string

Overrides the backend-specific default mount path. When empty, the operator selects a default appropriate for the backend framework.

eppConfig
EPPConfigDeprecated

Deprecated: omit eppConfig and use the native Rust EPP, which is configured through environment variables and takes no config file. Presence of this field selects the legacy Go EPP pod contract, so existing deployments keep running across an operator upgrade until you clear it.

Only valid when type is epp, and its use is decided by the component’s resolved runtime version: required below 1.5.0 (legacy Go EPP image), forbidden at 1.5.0 and later (native Rust EPP image). Migrate by clearing eppConfig and moving to a 1.5.0+ image in the same update. Exactly one of configMapRef or config must be set. See the Gateway API Routing Reference.

configMapRef
core/v1.ConfigMapKeySelector

References a user-provided ConfigMap key containing EPP configuration. Mutually exclusive with config.

core/v1.ConfigMapKeySelector
config
EndpointPickerConfig

EPP EndpointPickerConfig supplied inline. The operator marshals it to YAML and creates the ConfigMap for you. Mutually exclusive with configMapRef.

topologyConstraint
TopologyConstraint

Component-level topology placement. See the SpecTopologyConstraint API.

packDomain
stringRequired

Topology domain to pack pods within. Must match a domain defined in the referenced ClusterTopology. When the parent DGD also sets spec.topologyConstraint.packDomain, this value must be narrower than or equal to it.

experimental
ExperimentalSpec

Opt-in preview features whose API shape may change in breaking ways between v1beta1 releases. Fields here are not covered by the normal v1beta1 deprecation policy — do not rely on them for production workloads.

See: ExperimentalSpec

Runtime Version Compatibility

DGD admission requires runtimeVersionOverride when the main image has no parseable semantic-version tag. Also set it when a parseable tag does not represent the Dynamo runtime version in the image. The override must describe the Dynamo runtime actually contained in the image.

When updating an image to a different Dynamo runtime version, update any configured runtimeVersionOverride in the same change, or remove it if the new image tag correctly identifies the runtime version. The operator uses the resolved runtime version to select feature gates that control how it renders the component’s PodSpec, including flags, environment variables, and probes. For Dynamo 1.5.0 and later, changing the override alone may change the rendered PodSpec or worker revision and trigger a rollout, even when the image reference is unchanged. Keep the override aligned with the Dynamo runtime actually contained in the image.

For components generated by a DGDR, an explicit component override takes precedence over the DGDR-level default. See Profiler image version compatibility.

Status

The operator maintains observed state under status.

status.conditions
[]metav1.Condition

Standard Kubernetes conditions. Available reports whether the component is serving traffic; DynamoComponentReady reports whether the underlying Dynamo component is ready.

metav1.Condition
status.observedGeneration
integer

Most recent metadata.generation the controller has reconciled. A component is up to date when this equals metadata.generation.

status.component
ComponentReplicaStatus

Replica status for this component: desired, ready, and available counts. Shares the shape documented on the DGD Reference.

Additional Types

Nested struct types referenced by the fields above, broken out here to keep the field lists shallow. Types prefixed core/v1., metav1., resource., or runtime. are standard Kubernetes types and link to their Go package documentation instead of being expanded.

ExperimentalSpec

Groups opt-in preview features for a component. Referenced by experimental. Nested types (GMSClientPodSpec, ComponentCheckpointJobConfig, DynamoCheckpointIdentity) are expanded inline under the field that references them.

These preview features can change or disappear between v1beta1 releases without a name-preserving graduation path. They are excluded from the v1beta1 deprecation policy — do not rely on them for production workloads.

gpuMemoryService
GPUMemoryServiceSpec

Configures the GPU Memory Service (GMS). When set, GPU access for GMS clients is managed through Dynamic Resource Allocation (DRA), and the operator replaces the main container’s GPU resources with a DRA ResourceClaim.

mode
GPUMemoryServiceModeDefaults to IntraPod

Selects the GMS deployment topology.

Allowed values: IntraPod InterPod
deviceClassName
stringDefaults to gpu.nvidia.com

The DRA DeviceClass to request GPUs from.

extraClientContainers
[]string

Additional user-declared containers that should be wired as GMS clients in service pods. SnapshotJob capture Pod clients are declared under checkpoint.job.gmsClientContainers instead. In each rendered pod, only matching container names are wired; absent names are ignored. Each name must match ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$, 1–63 characters.

extraClientPods
[]GMSClientPodSpec

Additional GMS client pods for inter-pod GMS. Reserved for future use and rejected until inter-pod client orchestration is wired.

name
stringRequired

Identifies this client pod. Must match ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$, 1–63 characters.

podTemplate
core/v1.PodTemplateSpecRequired

Configures the pod to run as a GMS client.

core/v1.PodTemplateSpec
failover
FailoverSpec

Configures active-passive GPU failover for a worker component. The main container is cloned into two engine containers (active + standby) sharing GPUs via DRA, and the standby acquires the flock when the active engine fails. Requires gpuMemoryService to be set, failover.mode to match gpuMemoryService.mode, and the nvidia.com/dynamo-kube-discovery-mode: container annotation on the DGD.

mode
GPUMemoryServiceModeDefaults to IntraPod

Failover deployment topology. Must match the GMS mode on the same component.

Allowed values: IntraPod InterPod
numShadows
integerDefaults to 1

Number of shadow (standby) engine containers per rank. Reserved for future use; the operator currently creates exactly one shadow. Minimum 1, maximum 1.

grove
GroveSpec

Configures experimental Grove workload rendering for a component in a DGD. Requires the Grove pathway.

forceScalingGroup
boolean

When true, renders a single-node component as a PodCliqueScalingGroup with one single-pod PodClique per replica. The first minAvailable replicas join the deployment’s base PodGang; each additional replica gets a separate PodGang. false or omission retains automatic selection: multinode and inter-pod GMS components use scaling groups, while other single-node components use a PodClique. Immutable after creation.

checkpoint
ComponentCheckpointConfig

Configures container-image snapshotting and restore for the component. Set checkpoint.enabled: true to opt in; omit checkpointRef for a DGD-managed automatic checkpoint, or set it to restore a PodSnapshot in the same namespace.

This release is a hard compatibility boundary for checkpoint resources. Dynamo creates automatic captures through the standalone Snapshot operator’s SnapshotJob API, and checkpointRef names a standalone PodSnapshot. Legacy DynamoCheckpoint objects and their artifacts cannot be restored.

The upgrade does not delete the legacy DynamoCheckpoint CRD, instances, PodSnapshot objects, PodSnapshotContent objects, PVC data, or stored artifacts. Before upgrading, list retained DynamoCheckpoint objects and legacy PodSnapshot objects labeled nvidia.com/snapshot-owner, recreate any required snapshots through the standalone Snapshot APIs, and delete unneeded legacy checkpoints while the old controller can still run their finalizers. After upgrading, review and remove unsupported resources manually. Do not delete the shared PodSnapshot or PodSnapshotContent CRDs because the standalone Snapshot operator uses them.

enabled
booleanRequired

Whether checkpointing is enabled for this component. When true, omit checkpointRef for a DGD-managed automatic checkpoint, or set checkpointRef to restore a PodSnapshot in the same namespace. Omit the checkpoint block, or set enabled: false, to disable checkpointing.

startupPolicy
CheckpointStartupPolicyDefaults to Immediate

When normal worker replicas are started relative to automatic checkpoint readiness. Immediate starts workers cold immediately, and later pods restore from the checkpoint once it is Ready. WaitForCheckpoint keeps worker replicas at zero until the checkpoint is Ready, then starts them from it.

Allowed values: Immediate WaitForCheckpoint
deletionPolicy
CheckpointDeletionPolicyDefaults to Delete

Whether a DGD-managed automatic checkpoint CR and artifact are deleted or retained when the owning DGD is deleted. Explicit checkpointRef PodSnapshots are never owned or deleted by the DGD, and retained automatic checkpoints are not valid checkpointRef targets.

Allowed values: Delete Retain
checkpointRef
string

References an existing PodSnapshot in the same namespace by metadata.name. When set, this component’s identity is ignored and the referenced PodSnapshot is used directly. Standalone worker-class (worker, prefill, or decode) DynamoComponentDeployment resources cannot set this field; configure checkpointRef on the component in the owning DynamoGraphDeployment.

targetContainerName
stringDefaults to main

The workload container to snapshot and restore. Must match ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$, 1–63 characters.

job
ComponentCheckpointJobConfig

Customizes the DGD-managed SnapshotJob capture Pod.

gmsClientContainers
[]string

SnapshotJob capture Pod containers that should receive GMS client wiring. Requires gpuMemoryService on the component. Each name must match ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$, 1–63 characters.

podTemplate
core/v1.PodTemplateSpec

Customizes the SnapshotJob capture Pod. The operator starts from the selected workload container and merges this template, so you can add helper containers such as gms-saver.

core/v1.PodTemplateSpec
mode
CheckpointModeDeprecated

Deprecated: omit mode. Use enabled: true without checkpointRef for a DGD-managed automatic checkpoint, or use checkpointRef to restore a named PodSnapshot.

Allowed values: Auto Manual
identity
DynamoCheckpointIdentityDeprecated

Deprecated: omit for DGD-managed checkpoints; the operator ignores this field. Use checkpointRef to restore an existing PodSnapshot.

model
stringDeprecatedRequired

Model identifier, for example meta-llama/Llama-3-70B.

backendFramework
stringDeprecatedRequired

Runtime framework.

Allowed values: vllm sglang trtllm
dynamoVersion
stringDeprecated

Dynamo platform version.

tensorParallelSize
integerDefaults to 1Deprecated

Tensor parallel configuration. Deprecated: checkpoint launch uses the pod template instead. Minimum 1.

pipelineParallelSize
integerDefaults to 1Deprecated

Pipeline parallel configuration. Deprecated: checkpoint launch uses the pod template instead. Minimum 1.

dtype
stringDeprecated

Data type, for example fp16, bf16, or fp8.

maxModelLen
integerDeprecated

Maximum sequence length. Minimum 1.

extraParameters
map[string]stringDeprecated

Additional parameters that affect the checkpoint hash.

Inspect a DCD

# List component deployments (short name: dcd)
kubectl get dcd -n $NAMESPACE
# Detailed status and conditions
kubectl describe dcd my-worker -n $NAMESPACE
# Readiness at a glance
kubectl get dcd my-worker -n $NAMESPACE \
-o jsonpath='{.status.conditions[?(@.type=="Available")].status}'