From 1537a36f0313ee9b2a25a39942e619e0b54cd2d4 Mon Sep 17 00:00:00 2001 From: Shantanu Tripathi Date: Wed, 3 Sep 2025 23:01:54 +0000 Subject: [PATCH 1/2] Upgrade helm version with new CRD changes --- .../charts/inference-operator/Chart.yaml | 2 +- ...s.amazon.com_inferenceendpointconfigs.yaml | 36 +++++++++++++++++-- ...emaker.aws.amazon.com_jumpstartmodels.yaml | 22 ++++++++++-- ...on.com_sagemakerendpointregistrations.yaml | 4 +++ 4 files changed, 59 insertions(+), 5 deletions(-) diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml index 48c2b979..52458aa2 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml @@ -21,7 +21,7 @@ version: 0.1.0 # incremented each time you make changes to the application. Versions are not expected to # follow Semantic Versioning. They should reflect the version the application is using. # It is recommended to use it with quotes. -appVersion: "1.16.0" +appVersion: "1.17.0" dependencies: - name: aws-mountpoint-s3-csi-driver diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml index de3f762e..7e881fde 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_inferenceendpointconfigs.yaml @@ -214,8 +214,8 @@ spec: type: object endpointName: description: |- - Name of a SageMaker endpoint to be created for this InferenceEndpointConfig. - The default value of empty string, when used, will skip endpoint creation. + Name used for Sagemaker Endpoint + Name of sagemaker endpoint. Defaults to empty string which represents that Sagemaker endpoint will not be created. maxLength: 63 pattern: ^$|^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$ type: string @@ -229,6 +229,24 @@ spec: The invocation endpoint of the model server. http://:/ would be pre-populated based on the other fields. Please fill in the path after http://:/ specific to your model server. type: string + loadBalancer: + description: Configuration for Application Load Balancer + properties: + healthCheckPath: + default: /ping + description: Health check path for the ALB target group. Defaults + to /ping if not specified. + pattern: ^/.* + type: string + routingAlgorithm: + default: least_outstanding_requests + description: Routing algorithm for the ALB target group (least_oustanding_requests + or round_robin) + enum: + - least_outstanding_requests + - round_robin + type: string + type: object metrics: description: Configuration for metrics collection and exposure properties: @@ -345,6 +363,17 @@ spec: worker: description: Details of the worker properties: + args: + description: Defines the Arguments to the entrypoint. + items: + type: string + type: array + command: + description: Defines the Command which is Entrypoint array. Not + executed within a shell. + items: + type: string + type: array environmentVariables: description: |- List of environment variables to set in the container. @@ -569,6 +598,9 @@ spec: More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object + workingDir: + description: Defines the working directory of container. + type: string required: - image - modelInvocationPort diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_jumpstartmodels.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_jumpstartmodels.yaml index 342de2bb..89be2167 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_jumpstartmodels.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_jumpstartmodels.yaml @@ -219,6 +219,24 @@ spec: type: object maxItems: 100 type: array + loadBalancer: + description: Configuration for Application Load Balancer + properties: + healthCheckPath: + default: /ping + description: Health check path for the ALB target group. Defaults + to /ping if not specified. + pattern: ^/.* + type: string + routingAlgorithm: + default: least_outstanding_requests + description: Routing algorithm for the ALB target group (least_oustanding_requests + or round_robin) + enum: + - least_outstanding_requests + - round_robin + type: string + type: object maxDeployTimeInSeconds: default: 3600 description: Maximum allowed time in seconds for the deployment to @@ -320,8 +338,8 @@ spec: properties: name: default: "" - description: Name of a SageMaker endpoint to be created for this JumpStartModel. - The default value of empty string, when used, will skip endpoint creation. + description: Name of sagemaker endpoint. Defaults to empty string + which represents that Sagemaker endpoint will not be created. maxLength: 63 pattern: ^$|^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$ type: string diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_sagemakerendpointregistrations.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_sagemakerendpointregistrations.yaml index 0ff9aca8..8475f44c 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_sagemakerendpointregistrations.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/crd/inference.sagemaker.aws.amazon.com_sagemakerendpointregistrations.yaml @@ -88,6 +88,10 @@ spec: description: InstanceType is the ML compute instance type used for EndpointConfig creation type: string + invocationEndpoint: + default: invocations + description: The invocation endpoint path used by the model server + type: string loadBalancerHostName: description: Needed to embed the LB Host Name type: string From c22c605fc5c63bb13ad891afc1ad52f837003329 Mon Sep 17 00:00:00 2001 From: Shantanu Tripathi Date: Thu, 4 Sep 2025 00:46:22 +0000 Subject: [PATCH 2/2] Adding version increment consumption as env variables --- .../HyperPodHelmChart/charts/inference-operator/Chart.yaml | 2 +- .../charts/inference-operator/config/manager/manager.yaml | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml index 52458aa2..a3a37eba 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml @@ -15,7 +15,7 @@ type: application # This is the chart version. This version number should be incremented each time you make changes # to the chart and its templates, including the app version. # Versions are expected to follow Semantic Versioning (https://semver.org/) -version: 0.1.0 +version: 0.2.0 # This is the version number of the application being deployed. This version number should be # incremented each time you make changes to the application. Versions are not expected to diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/manager/manager.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/manager/manager.yaml index daf62016..6420b1a8 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/config/manager/manager.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/config/manager/manager.yaml @@ -103,5 +103,9 @@ spec: value: {{ .Values.eksClusterName }} - name: TLS_CERTIFICATE_OUTPUT_S3URI value: {{ .Values.tlsCertificateS3Bucket }} + - name: CHART_VERSION + value: {{ .Chart.Version | quote }} + - name: APP_VERSION + value: {{ .Chart.AppVersion | quote }} serviceAccountName: {{ .Values.namePrefix }}-controller-manager terminationGracePeriodSeconds: 10