kserve: Dataflow¶
Controller Watches¶
Kubernetes resources this controller monitors for changes. Each watch triggers reconciliation when the watched resource is created, updated, or deleted.
Programmatic Resource Operations¶
| Verb | Kind | Group | Condition |
|---|---|---|---|
| create | ConfigMap | ||
| update | ConfigMap | ||
| update | LLMInferenceService | serving | |
| patch | LocalModelCache | serving | |
| patch | LocalModelNamespaceCache | serving | |
| create | Deployment | apps | |
| patch | Deployment | apps | |
| delete | Deployment | apps | |
| delete | HTTPRoute | apis | |
| create | HTTPRoute | apis | |
| update | HTTPRoute | apis | |
| create | VirtualService | networking | |
| update | VirtualService | networking | |
| delete | VirtualService | networking | |
| create | Service | ||
| update | Service | ||
| delete | Service | ||
| delete | Ingress | networking.k8s.io | |
| create | Ingress | networking.k8s.io | |
| update | Ingress | networking.k8s.io | |
| create | HorizontalPodAutoscaler | autoscaling | |
| update | HorizontalPodAutoscaler | autoscaling | |
| delete | HorizontalPodAutoscaler | autoscaling | |
| delete | ScaledObject | keda | |
| create | ScaledObject | keda | |
| update | ScaledObject | keda | |
| delete | OpenTelemetryCollector | apis | |
| create | OpenTelemetryCollector | apis | |
| update | OpenTelemetryCollector | apis | |
| patch | InferenceGraph | serving | |
| delete | Service | serving | |
| update | Service | serving | |
| create | Service | serving | |
| delete | Route | route | |
| create | Route | route | |
| update | Route | route | |
| delete | TrainedModel | serving | |
| update | TrainedModel | serving | |
| patch | InferenceService | serving |
Reconciliation Flow¶
How the controller interacts with the Kubernetes API during reconciliation.
sequenceDiagram
%% Static dataflow for kserve
participant KubernetesAPI as Kubernetes API
participant keda_metrics_apiserver as keda-metrics-apiserver
participant keda_operator as keda-operator
participant kserve_controller_manager as kserve-controller-manager
participant kserve_localmodel_controller_manager as kserve-localmodel-controller-manager
participant llama_deployment as llama-deployment
participant llmisvc_controller_manager as llmisvc-controller-manager
KubernetesAPI->>+keda_metrics_apiserver: Watch ConfigMap (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ConfigMap (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ConfigMap (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ConfigMap (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch Pod (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch Pod (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch Pod (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch Pod (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch VariantAutoscaling (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch VariantAutoscaling (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch OpAMPBridge (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch OpAMPBridge (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch TargetAllocator (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch TargetAllocator (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch OpenTelemetryCollector (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch OpenTelemetryCollector (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceModelRewrite (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceModelRewrite (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceObjective (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceObjective (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferencePool (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch CloudEventSource (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch CloudEventSource (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ClusterCloudEventSource (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ClusterCloudEventSource (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ClusterTriggerAuthentication (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ClusterTriggerAuthentication (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ScaledJob (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ScaledJob (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ScaledObject (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch ScaledObject (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch TriggerAuthentication (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch TriggerAuthentication (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LeaderWorkerSet (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LeaderWorkerSet (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceGraph (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LocalModelCache (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LocalModelNamespaceCache (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LocalModelNode (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch TrainedModel (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch LLMInferenceService (reconcile)
KubernetesAPI->>+keda_metrics_apiserver: Watch InferenceService (reconcile)
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update ConfigMap
keda_metrics_apiserver->>KubernetesAPI: Create/Update PersistentVolume
keda_metrics_apiserver->>KubernetesAPI: Create/Update PersistentVolumeClaim
keda_metrics_apiserver->>KubernetesAPI: Create/Update PersistentVolumeClaim
keda_metrics_apiserver->>KubernetesAPI: Create/Update Secret
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceAccount
keda_metrics_apiserver->>KubernetesAPI: Create/Update InferencePool
keda_metrics_apiserver->>KubernetesAPI: Create/Update VariantAutoscaling
keda_metrics_apiserver->>KubernetesAPI: Create/Update HTTPRoute
keda_metrics_apiserver->>KubernetesAPI: Create/Update HTTPRoute
keda_metrics_apiserver->>KubernetesAPI: Create/Update OpenTelemetryCollector
keda_metrics_apiserver->>KubernetesAPI: Create/Update InferencePool
keda_metrics_apiserver->>KubernetesAPI: Create/Update DaemonSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update DaemonSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update Deployment
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update StatefulSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update HorizontalPodAutoscaler
keda_metrics_apiserver->>KubernetesAPI: Create/Update HorizontalPodAutoscaler
keda_metrics_apiserver->>KubernetesAPI: Create/Update HorizontalPodAutoscaler
keda_metrics_apiserver->>KubernetesAPI: Create/Update HorizontalPodAutoscaler
keda_metrics_apiserver->>KubernetesAPI: Create/Update HorizontalPodAutoscaler
keda_metrics_apiserver->>KubernetesAPI: Create/Update Job
keda_metrics_apiserver->>KubernetesAPI: Create/Update ScaledObject
keda_metrics_apiserver->>KubernetesAPI: Create/Update ScaledObject
keda_metrics_apiserver->>KubernetesAPI: Create/Update LeaderWorkerSet
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update ServiceMonitor
keda_metrics_apiserver->>KubernetesAPI: Create/Update Ingress
keda_metrics_apiserver->>KubernetesAPI: Create/Update Ingress
keda_metrics_apiserver->>KubernetesAPI: Create/Update Ingress
keda_metrics_apiserver->>KubernetesAPI: Create/Update Ingress
keda_metrics_apiserver->>KubernetesAPI: Create/Update VirtualService
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodDisruptionBudget
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodDisruptionBudget
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodDisruptionBudget
keda_metrics_apiserver->>KubernetesAPI: Create/Update PodDisruptionBudget
keda_metrics_apiserver->>KubernetesAPI: Create/Update ClusterRole
keda_metrics_apiserver->>KubernetesAPI: Create/Update ClusterRole
keda_metrics_apiserver->>KubernetesAPI: Create/Update ClusterRoleBinding
keda_metrics_apiserver->>KubernetesAPI: Create/Update ClusterRoleBinding
keda_metrics_apiserver->>KubernetesAPI: Create/Update Route
keda_metrics_apiserver->>KubernetesAPI: Create/Update Route
keda_metrics_apiserver->>KubernetesAPI: Create/Update Route
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
keda_metrics_apiserver->>KubernetesAPI: Create/Update Service
KubernetesAPI-->>+keda_metrics_apiserver: Watch ConfigMap (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch Node (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch Node (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch Pod (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch Pod (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch Gateway (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch HTTPRoute (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch StatefulSet (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch StatefulSet (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch ClusterServingRuntime (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch LocalModelNode (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch LocalModelNode (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch ServingRuntime (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch LLMInferenceServiceConfig (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch InferenceService (informer)
KubernetesAPI-->>+keda_metrics_apiserver: Watch InferenceService (informer)
Note over keda_metrics_apiserver: Exposed Services
Note right of keda_metrics_apiserver: cli-port-default:80/TCP []
Note right of keda_metrics_apiserver: keda-admission-webhooks:443/TCP [https]
Note right of keda_metrics_apiserver: keda-admission-webhooks:8080/TCP [metrics]
Note right of keda_metrics_apiserver: keda-admission-webhooks:443/TCP [https]
Note right of keda_metrics_apiserver: keda-admission-webhooks:8080/TCP [metrics]
Note right of keda_metrics_apiserver: keda-metrics-apiserver:443/TCP [https]
Note right of keda_metrics_apiserver: keda-metrics-apiserver:8080/TCP [metrics]
Note right of keda_metrics_apiserver: keda-metrics-apiserver:443/TCP [https]
Note right of keda_metrics_apiserver: keda-metrics-apiserver:8080/TCP [metrics]
Note right of keda_metrics_apiserver: keda-operator:9666/TCP [metricsservice]
Note right of keda_metrics_apiserver: keda-operator:8080/TCP [metrics]
Note right of keda_metrics_apiserver: keda-operator:9666/TCP [metricsservice]
Note right of keda_metrics_apiserver: keda-operator:8080/TCP [metrics]
Note right of keda_metrics_apiserver: kserve-controller-manager-metrics-service:8443/TCP [https]
Note right of keda_metrics_apiserver: kserve-controller-manager-service:8443/TCP []
Note right of keda_metrics_apiserver: kserve-webhook-server-service:443/TCP []
Note right of keda_metrics_apiserver: llmisvc-controller-manager-service:8443/TCP [https]
Note right of keda_metrics_apiserver: llmisvc-webhook-server-service:443/TCP [https]
Note right of keda_metrics_apiserver: localmodel-webhook-server-service:443/TCP []
Note right of keda_metrics_apiserver: uvicorn-server:8000/TCP []
Note right of keda_metrics_apiserver: webhook-service:443/TCP []
Note right of keda_metrics_apiserver: webhook-service:443/TCP []
Note right of keda_metrics_apiserver: webhook-service:443/TCP []
Note right of keda_metrics_apiserver: webhook-service:443/TCP []
Note over KubernetesAPI: Defined CRDs
Note right of KubernetesAPI: ClusterServingRuntime (/v1alpha1)
Note right of KubernetesAPI: ClusterStorageContainer (/v1alpha1)
Note right of KubernetesAPI: InferenceGraph (/v1alpha1)
Note right of KubernetesAPI: LLMInferenceService (/v1alpha1)
Note right of KubernetesAPI: LLMInferenceServiceConfig (/v1alpha1)
Note right of KubernetesAPI: LocalModelCache (/v1alpha1)
Note right of KubernetesAPI: LocalModelNamespaceCache (/v1alpha1)
Note right of KubernetesAPI: LocalModelNode (/v1alpha1)
Note right of KubernetesAPI: LocalModelNodeGroup (/v1alpha1)
Note right of KubernetesAPI: ServingRuntime (/v1alpha1)
Note right of KubernetesAPI: TrainedModel (/v1alpha1)
Note right of KubernetesAPI: LLMInferenceService (/v1alpha2)
Note right of KubernetesAPI: LLMInferenceServiceConfig (/v1alpha2)
Note right of KubernetesAPI: InferenceService (/v1beta1)
Note right of KubernetesAPI: ClusterServingRuntime (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: ClusterStorageContainer (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: InferenceGraph (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: LocalModelCache (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: LocalModelNamespaceCache (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: LocalModelNode (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: LocalModelNodeGroup (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: ServingRuntime (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: TrainedModel (serving.kserve.io/v1alpha1)
Note right of KubernetesAPI: LLMInferenceService (serving.kserve.io/v1alpha2)
Note right of KubernetesAPI: LLMInferenceServiceConfig (serving.kserve.io/v1alpha2)
Note right of KubernetesAPI: InferenceService (serving.kserve.io/v1beta1)
Webhooks¶
llminferenceservice.kserve-webhook-server.v1alpha1.validator Behavior¶
| Field | Operation | Condition |
|---|---|---|
| spec | invalid | |
| worker | invalid | |
| dataLocal | invalid | |
| data | invalid | |
| pipeline | invalid | |
| replicas | invalid | |
| inline | invalid | |
| ref.name | invalid |
llminferenceservice.kserve-webhook-server.v1alpha2.validator Behavior¶
| Field | Operation | Condition |
|---|---|---|
| spec | invalid | |
| worker | invalid | |
| dataLocal | invalid | |
| data | invalid | |
| pipeline | invalid | |
| replicas | invalid | |
| inline | invalid | |
| ref.name | invalid |
llminferenceserviceconfig.kserve-webhook-server.v1alpha1.validator Behavior¶
| Field | Operation | Condition |
|---|---|---|
| spec.baseRefs | forbidden | |
| replicas | invalid |
llminferenceserviceconfig.kserve-webhook-server.v1alpha2.validator Behavior¶
| Field | Operation | Condition |
|---|---|---|
| spec.baseRefs | forbidden | |
| replicas | invalid |
HTTP Endpoints¶
Configuration¶
ConfigMaps and Helm values that control this component's runtime behavior.
ConfigMaps¶
| Name | Data Keys | Source |
|---|---|---|
| inferenceservice-config | _example, agent, autoscaler, batcher, credentials, deploy, explainers, inferenceService, ingress, localModel, logger, metricsAggregator, opentelemetryCollector, router, security, storageInitializer | charts/kserve-resources/files/common/configmap.yaml |
| inferenceservice-config | agent, autoscaler, batcher, credentials, deploy, explainers, inferenceService, ingress, localModel, logger, metricsAggregator, opentelemetryCollector, router, security, service, storageInitializer | charts/kserve-resources/files/common/configmap-patch.yaml |
| inferenceservice-config | _example, agent, autoscaler, batcher, credentials, deploy, explainers, inferenceService, ingress, localModel, logger, metricsAggregator, opentelemetryCollector, router, security, storageInitializer | charts/kserve-llmisvc-resources/files/common/configmap.yaml |
| inferenceservice-config | agent, autoscaler, batcher, credentials, deploy, explainers, inferenceService, ingress, localModel, logger, metricsAggregator, opentelemetryCollector, router, security, service, storageInitializer | charts/kserve-llmisvc-resources/files/common/configmap-patch.yaml |
| inferenceservice-config | agent, autoscaler, batcher, credentials, deploy, explainers, inferenceService, ingress, localModel, logger, metricsAggregator, opentelemetryCollector, router, security, service, storageInitializer | charts/_common/common-patches/configmap-patch.yaml |
| saturation-scaling-config | default | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/manager/configmap-saturation-scaling.yaml |
| saturation-scaling-config | default | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/manager/configmap-saturation-scaling.yaml |
| service-classes-config | freemium.yaml, premium.yaml | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-serviceclass.yaml |
| service-classes-config | freemium.yaml, premium.yaml | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-serviceclass.yaml |
| wva-queueing-model-config | default | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-queueing-model.yaml |
| wva-queueing-model-config | default | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-queueing-model.yaml |
| wva-saturation-scaling-config | default | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-saturation-scaling.yaml |
| wva-saturation-scaling-config | default | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/deploy/configmap-saturation-scaling.yaml |
| wva-variantautoscaling-config | GLOBAL_OPT_INTERVAL, PROMETHEUS_BASE_URL, PROMETHEUS_METRICS_CACHE_CLEANUP_INTERVAL, PROMETHEUS_METRICS_CACHE_FETCH_INTERVAL, PROMETHEUS_METRICS_CACHE_FRESH_THRESHOLD, PROMETHEUS_METRICS_CACHE_STALE_THRESHOLD, PROMETHEUS_METRICS_CACHE_TTL, PROMETHEUS_METRICS_CACHE_UNAVAILABLE_THRESHOLD, PROMETHEUS_TLS_INSECURE_SKIP_VERIFY | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/openshift/configmap-patch.yaml |
| wva-variantautoscaling-config | GLOBAL_OPT_INTERVAL, PROMETHEUS_BASE_URL, PROMETHEUS_METRICS_CACHE_CLEANUP_INTERVAL, PROMETHEUS_METRICS_CACHE_FETCH_INTERVAL, PROMETHEUS_METRICS_CACHE_FRESH_THRESHOLD, PROMETHEUS_METRICS_CACHE_MAX_SIZE, PROMETHEUS_METRICS_CACHE_STALE_THRESHOLD, PROMETHEUS_METRICS_CACHE_TTL, PROMETHEUS_METRICS_CACHE_UNAVAILABLE_THRESHOLD, PROMETHEUS_TLS_INSECURE_SKIP_VERIFY, WVA_LIMITED_MODE, WVA_NODE_SELECTOR, WVA_SCALE_TO_ZERO | .gopath-loader/pkg/mod/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/manager/configmap.yaml |
| wva-variantautoscaling-config | GLOBAL_OPT_INTERVAL, PROMETHEUS_BASE_URL, PROMETHEUS_METRICS_CACHE_CLEANUP_INTERVAL, PROMETHEUS_METRICS_CACHE_FETCH_INTERVAL, PROMETHEUS_METRICS_CACHE_FRESH_THRESHOLD, PROMETHEUS_METRICS_CACHE_STALE_THRESHOLD, PROMETHEUS_METRICS_CACHE_TTL, PROMETHEUS_METRICS_CACHE_UNAVAILABLE_THRESHOLD, PROMETHEUS_TLS_INSECURE_SKIP_VERIFY | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/openshift/configmap-patch.yaml |
| wva-variantautoscaling-config | GLOBAL_OPT_INTERVAL, PROMETHEUS_BASE_URL, PROMETHEUS_METRICS_CACHE_CLEANUP_INTERVAL, PROMETHEUS_METRICS_CACHE_FETCH_INTERVAL, PROMETHEUS_METRICS_CACHE_FRESH_THRESHOLD, PROMETHEUS_METRICS_CACHE_MAX_SIZE, PROMETHEUS_METRICS_CACHE_STALE_THRESHOLD, PROMETHEUS_METRICS_CACHE_TTL, PROMETHEUS_METRICS_CACHE_UNAVAILABLE_THRESHOLD, PROMETHEUS_TLS_INSECURE_SKIP_VERIFY, WVA_LIMITED_MODE, WVA_NODE_SELECTOR, WVA_SCALE_TO_ZERO | .gomod-cache/github.com/llm-d/llm-d-workload-variant-autoscaler@v0.6.0/config/manager/configmap.yaml |
Helm¶
Chart: workload-variant-autoscaler v0.5.1