⚠️ Important: This documentation is automatically generated from source code. Do not edit this file directly.
API Reference#
Packages#
nvidia.com/v1alpha1#
Package v1alpha1 contains API Schema definitions for the nvidia.com v1alpha1 API group.
Resource Types#
Autoscaling#
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
|||
|
|||
|
|||
|
|||
|
DynamoComponentDeployment#
DynamoComponentDeployment is the Schema for the dynamocomponentdeployments API
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
|
||
|
|
||
|
Refer to Kubernetes API documentation for fields of |
||
Spec defines the desired state for this Dynamo component deployment. |
DynamoComponentDeploymentSpec#
DynamoComponentDeploymentSpec defines the desired state of DynamoComponentDeployment
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
BackendFramework specifies the backend framework (e.g., “sglang”, “vllm”, “trtllm”) |
Enum: [sglang vllm trtllm] |
|
|
Annotations to add to generated Kubernetes resources for this component |
||
|
Labels to add to generated Kubernetes resources for this component. |
||
|
The name of the component |
||
|
ComponentType indicates the role of this component (for example, “main”). |
||
|
SubComponentType indicates the sub-role of this component (for example, “prefill”). |
||
|
Dynamo namespace of the service (allows to override the Dynamo namespace of the service defined in annotations inside the Dynamo archive) |
||
|
Resources requested and limits for this component, including CPU, memory, |
||
|
Autoscaling config for this component (replica range, target utilization, etc.). |
||
|
Envs defines additional environment variables to inject into the component containers. |
||
|
EnvFromSecret references a Secret whose key/value pairs will be exposed as |
||
|
VolumeMounts references PVCs defined at the top level for volumes to be mounted by the component. |
||
|
Ingress config to expose the component outside the cluster (or through a service mesh). |
||
|
SharedMemory controls the tmpfs mounted at /dev/shm (enable/disable and size). |
||
|
ExtraPodMetadata adds labels/annotations to the created Pods. |
||
|
ExtraPodSpec allows to override the main pod spec configuration. |
||
|
LivenessProbe to detect and restart unhealthy containers. |
||
|
ReadinessProbe to signal when the container is ready to receive traffic. |
||
|
Replicas is the desired number of Pods for this component when autoscaling is not used. |
||
|
Multinode is the configuration for multinode components. |
DynamoGraphDeployment#
DynamoGraphDeployment is the Schema for the dynamographdeployments API.
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
|
||
|
|
||
|
Refer to Kubernetes API documentation for fields of |
||
Spec defines the desired state for this graph deployment. |
|||
|
Status reflects the current observed state of this graph deployment. |
DynamoGraphDeploymentSpec#
DynamoGraphDeploymentSpec defines the desired state of DynamoGraphDeployment.
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
PVCs defines a list of persistent volume claims that can be referenced by components. |
Optional: {} |
|
|
Services are the services to deploy as part of this deployment. |
Optional: {} |
|
|
Envs are environment variables applied to all services in the deployment unless |
Optional: {} |
|
|
BackendFramework specifies the backend framework (e.g., “sglang”, “vllm”, “trtllm”). |
Enum: [sglang vllm trtllm] |
DynamoGraphDeploymentStatus#
DynamoGraphDeploymentStatus defines the observed state of DynamoGraphDeployment.
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
State is a high-level textual status of the graph deployment lifecycle. |
||
|
Conditions contains the latest observed conditions of the graph deployment. |
IngressSpec#
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
Enabled exposes the component through an ingress or virtual service when true. |
||
|
Host is the base host name to route external traffic to this component. |
||
|
UseVirtualService indicates whether to configure a service-mesh VirtualService instead of a standard Ingress. |
||
|
VirtualServiceGateway optionally specifies the gateway name to attach the VirtualService to. |
||
|
HostPrefix is an optional prefix added before the host. |
||
|
Annotations to set on the generated Ingress/VirtualService resources. |
||
|
Labels to set on the generated Ingress/VirtualService resources. |
||
|
TLS holds the TLS configuration used by the Ingress/VirtualService. |
||
|
HostSuffix is an optional suffix appended after the host. |
||
|
IngressControllerClassName selects the ingress controller class (e.g., “nginx”). |
IngressTLSSpec#
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
SecretName is the name of a Kubernetes Secret containing the TLS certificate and key. |
MultinodeSpec#
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
Indicates the number of nodes to deploy for multinode components. |
2 |
Minimum: 2 |
PVC#
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
Create indicates to create a new PVC |
||
|
Name is the name of the PVC |
Required: {} |
|
|
StorageClass to be used for PVC creation. Required when create is true. |
||
|
Size of the volume in Gi, used during PVC creation. Required when create is true. |
||
|
VolumeAccessMode is the volume access mode of the PVC. Required when create is true. |
VolumeMount#
VolumeMount references a PVC defined at the top level for volumes to be mounted by the component
Appears in:
Field |
Description |
Default |
Validation |
|---|---|---|---|
|
Name references a PVC name defined in the top-level PVCs map |
Required: {} |
|
|
MountPoint specifies where to mount the volume. |
||
|
UseAsCompilationCache indicates this volume should be used as a compilation cache. |
false |
Operator Default Values Injection#
The Dynamo operator automatically applies default values to various fields when they are not explicitly specified in your deployments. These defaults include:
Health Probes: Startup, liveness, and readiness probes are configured differently for frontend, worker, and planner components. For example, worker components receive a startup probe with a 2-hour timeout (720 failures × 10 seconds) to accommodate long model loading times.
Shared Memory: All components receive an 8Gi shared memory volume mounted at
/dev/shmby default (can be disabled or resized via thesharedMemoryfield).Environment Variables: Components automatically receive environment variables like
DYN_NAMESPACE,DYN_PARENT_DGD_K8S_NAME,DYNAMO_PORT, and backend-specific variables.Pod Configuration: Default
terminationGracePeriodSecondsof 60 seconds andrestartPolicy: Always.Autoscaling: When enabled without explicit metrics, defaults to CPU-based autoscaling with 80% target utilization.
Backend-Specific Behavior: For multinode deployments, probes are automatically modified or removed for worker nodes depending on the backend framework (VLLM, SGLang, or TensorRT-LLM).
Pod Specification Defaults#
All components receive the following pod-level defaults unless overridden:
terminationGracePeriodSeconds:60secondsrestartPolicy:Always
Health Probes by Component Type#
The operator applies different default health probes based on the component type.
Frontend Components#
Frontend components receive the following probe configurations:
Liveness Probe:
Type: HTTP GET
Path:
/healthPort:
http(8000)Initial Delay: 60 seconds
Period: 60 seconds
Timeout: 30 seconds
Failure Threshold: 10
Readiness Probe:
Type: Exec command
Command:
curl -s http://localhost:${DYNAMO_PORT}/health | jq -e ".status == \"healthy\""Initial Delay: 60 seconds
Period: 60 seconds
Timeout: 30 seconds
Failure Threshold: 10
Worker Components#
Worker components receive the following probe configurations:
Liveness Probe:
Type: HTTP GET
Path:
/livePort:
system(9090)Period: 5 seconds
Timeout: 30 seconds
Failure Threshold: 1
Readiness Probe:
Type: HTTP GET
Path:
/healthPort:
system(9090)Period: 10 seconds
Timeout: 30 seconds
Failure Threshold: 60
Startup Probe:
Type: HTTP GET
Path:
/livePort:
system(9090)Period: 10 seconds
Timeout: 5 seconds
Failure Threshold: 720 (allows up to 2 hours for startup: 10s × 720 = 7200s)
Note
For larger models (typically >70B parameters) or slower storage systems, you may need to increase the failureThreshold to allow more time for model loading. Calculate the required threshold based on your expected startup time: failureThreshold = (expected_startup_seconds / period). Override the startup probe in your component specification if the default 2-hour window is insufficient.
Multinode Deployment Probe Modifications#
For multinode deployments, the operator modifies probes based on the backend framework and node role:
VLLM Backend#
Worker nodes: All probes (liveness, readiness, startup) are removed
SGLang Backend#
Worker nodes: All probes (liveness, readiness, startup) are removed
TensorRT-LLM Backend#
Leader nodes: All probes remain unchanged
Worker nodes:
Liveness and startup probes are removed
Readiness probe is replaced with a TCP socket check on SSH port (2222):
Initial Delay: 20 seconds
Period: 20 seconds
Timeout: 5 seconds
Failure Threshold: 10
Environment Variables#
The operator automatically injects environment variables based on component type and configuration:
All Components#
DYN_NAMESPACE: The Dynamo namespace for the componentDYN_PARENT_DGD_K8S_NAME: The parent DynamoGraphDeployment Kubernetes resource nameDYN_PARENT_DGD_K8S_NAMESPACE: The parent DynamoGraphDeployment Kubernetes namespace
Frontend Components#
DYNAMO_PORT:8000DYN_HTTP_PORT:8000
Worker Components#
DYN_SYSTEM_ENABLED:trueDYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS:["generate"]DYN_SYSTEM_PORT:9090
Planner Components#
PLANNER_PROMETHEUS_PORT:9085
VLLM Backend (with compilation cache)#
When a volume mount is configured with useAsCompilationCache: true:
VLLM_CACHE_ROOT: Set to the mount point of the cache volume
Service Account#
Planner components automatically receive the following service account:
serviceAccountName:planner-serviceaccount
Image Pull Secrets#
The operator automatically discovers and injects image pull secrets for container images. When a component specifies a container image, the operator:
Scans all Kubernetes secrets of type
kubernetes.io/dockerconfigjsonin the component’s namespaceExtracts the docker registry server URLs from each secret’s authentication configuration
Matches the container image’s registry host against the discovered registry URLs
Automatically injects matching secrets as
imagePullSecretsin the pod specification
This eliminates the need to manually specify image pull secrets for each component. The operator maintains an internal index of docker secrets and their associated registries, refreshing this index periodically.
To disable automatic image pull secret discovery for a specific component, add the following annotation:
annotations:
nvidia.com/disable-image-pull-secret-discovery: "true"
Autoscaling Defaults#
When autoscaling is enabled but no metrics are specified, the operator applies:
Default Metric: CPU utilization
Target Average Utilization:
80%
Port Configurations#
Default container ports are configured based on component type:
Frontend Components#
Port: 8000
Protocol: TCP
Name:
http
Worker Components#
Port: 9090
Protocol: TCP
Name:
system
Planner Components#
Port: 9085
Protocol: TCP
Name:
metrics
Backend-Specific Configurations#
VLLM#
Ray Head Port: 6379 (for multinode deployments)
SGLang#
Distribution Init Port: 29500 (for multinode deployments)
TensorRT-LLM#
SSH Port: 2222 (for multinode MPI communication)
OpenMPI Environment:
OMPI_MCA_orte_keep_fqdn_hostnames=1
Implementation Reference#
For users who want to understand the implementation details or contribute to the operator, the default values described in this document are set in the following source files:
Health Probes & Pod Specifications:
internal/dynamo/graph.go- Contains the main logic for applying default probes, environment variables, shared memory, and pod configurationsComponent-Specific Defaults:
Image Pull Secrets:
internal/secrets/docker.go- Implements the docker secret indexer and automatic discoveryBackend-Specific Behavior:
Constants & Annotations:
internal/consts/consts.go- Defines annotation keys and other constants
Notes#
All these defaults can be overridden by explicitly specifying values in your DynamoComponentDeployment or DynamoGraphDeployment resources
User-specified probes (via
livenessProbe,readinessProbe, orstartupProbefields) take precedence over operator defaultsFor multinode deployments, some defaults are modified or removed as described above to accommodate distributed execution patterns
The
extraPodSpec.mainContainerfield can be used to override probe configurations set by the operator