Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

apiVersion: inference.sagemaker.aws.amazon.com/v1
kind: JumpStartModel
metadata:
  name: deepseek-sample624
  namespace: ns-team-a
spec:
  sageMakerEndpoint:
    name: deepsek7bsme624
  model:
    modelHubName: SageMakerPublicHub
    modelId: deepseek-llm-r1-distill-qwen-1-5b
    modelVersion: 2.0.4
  server:
    instanceType: ml.g5.8xlarge
  metrics:
    enabled: true
  environmentVariables:
    - name: SAMPLE_ENV_VAR
      value: "sample_value"
  maxDeployTimeInSeconds: 1800
  tlsConfig:
    tlsCertificateOutputS3Uri: "s3://{USER}-tls-bucket-{REGION}/certificates"
  autoScalingSpec:
    minReplicaCount: 0
    maxReplicaCount: 5
    pollingInterval: 15
    initialCooldownPeriod: 60
    cooldownPeriod: 120
    scaleDownStabilizationTime: 60
    scaleUpStabilizationTime: 0
    cloudWatchTrigger:
        name: "SageMaker-Invocations"
        namespace: "AWS/SageMaker"
        useCachedMetrics: false
        metricName: "Invocations"
        targetValue: 10.5
        activationTargetValue: 5.0
        minValue: 0.0
        metricCollectionStartTime: 300
        metricCollectionPeriod: 30
        metricStat: "Sum"
        metricType: "Average"
        dimensions:
          - name: "EndpointName"
            value: "deepsek7bsme624"
          - name: "VariantName"
            value: "AllTraffic"
    prometheusTrigger: 
        name: "Prometheus-Trigger"
        useCachedMetrics: false
        serverAddress: http://<prometheus-host>:9090
        query: sum(rate(http_requests_total{deployment="my-deployment"}[2m]))
        targetValue: 10.0
        activationTargetValue: 5.0
        namespace: "namespace"
        customHeaders: "X-Client-Id=cid"
        metricType: "Value"

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 1 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  triggers:
  - type: aws-cloudwatch
    metadata:
      namespace: AWS/SageMaker
      metricName: Invocations
      targetMetricValue: "1"
      minMetricValue: "1"
      awsRegion: "us-west-2"
      dimensionName: EndpointName;VariantName
      dimensionValue: $ENDPOINT_NAME;$VARIANT_NAME
      metricStatPeriod: "30" # seconds
      metricStat: "Sum"
      identityOwner: operator

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 1 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  triggers:
  - type: aws-sqs-queue
    metadata:
      queueURL: https://sqs.eu-west-1.amazonaws.com/account_id/QueueName
      queueLength: "5"  # Default: "5"
      awsRegion: "us-west-1"
      scaleOnInFlight: true
      identityOwner: operator

Metrik Prometheus

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 1 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  triggers:
  - type: prometheus
    metadata:
      serverAddress: http://<prometheus-host>:9090
      query: avg(rate(http_requests_total{deployment="$DEPLOYMENT_NAME"}[2m])) # Note: query must return a vector/scalar single element response
      threshold: '100.50'
      namespace: example-namespace  # for namespaced queries, eg. Thanos
      customHeaders: X-Client-Id=cid,X-Tenant-Id=tid,X-Organization-Id=oid # Optional. Custom headers to include in query. In case of auth header, use the custom authentication or relevant authModes.
      unsafeSsl: "false" #  Default is `false`, Used for skipping certificate check when having self-signed certs for Prometheus endpoint    
      timeout: 1000 # Custom timeout for the HTTP client used in this scaler
      identityOwner: operator

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 1 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  triggers:
  - type: cpu
    metricType: Utilization # Allowed types are 'Utilization' or 'AverageValue'
    metadata:
        value: "60"
        containerName: "" # Optional. You can use this to target a specific container

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 1 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  triggers:
  - type: memory
    metricType: Utilization # Allowed types are 'Utilization' or 'AverageValue'
    metadata:
        value: "60"
        containerName: "" # Optional. You can use this to target a specific container in a pod

apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: invocations-scaledobject # name of the scaled object that will be created by this
  namespace: ns-team-a # namespace that this scaled object targets
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: $DEPLOYMENT_NAME # name of the model deployment
  minReplicaCount: 0 # minimum number of pods to be maintained
  maxReplicaCount: 4 # maximum number of pods to scale to
  pollingInterval: 10
  cooldownPeriod:  30
  initialCooldownPeriod:  180 # time before scaling down the pods after initial deployment
  triggers:
  - type: prometheus
    metadata:
      serverAddress: http://<prometheus-host>:9090
      query: sum(rate(http_requests_total{deployment="my-deployment"}[2m])) # Note: query must return a vector/scalar single element response
      threshold: '100.50'
      activationThreshold: '5.5' # Required if minReplicaCount is 0 for initial scaling
      namespace: example-namespace
      timeout: 1000
      identityOwner: operator