From 9fcffef0dab393df85cde016c0d73a02640b9399 Mon Sep 17 00:00:00 2001 From: Shantanu Tripathi Date: Thu, 11 Dec 2025 20:00:25 +0000 Subject: [PATCH] Upgrade Inference Operator helm chart --- helm_chart/HyperPodHelmChart/Chart.yaml | 2 +- .../charts/inference-operator/Chart.yaml | 4 +- ...s.amazon.com_inferenceendpointconfigs.yaml | 468 ++++++++++++++++++ .../charts/inference-operator/values.yaml | 2 +- 4 files changed, 472 insertions(+), 4 deletions(-) diff --git a/helm_chart/HyperPodHelmChart/Chart.yaml b/helm_chart/HyperPodHelmChart/Chart.yaml index 366bff97..e89e3cb3 100644 --- a/helm_chart/HyperPodHelmChart/Chart.yaml +++ b/helm_chart/HyperPodHelmChart/Chart.yaml @@ -81,7 +81,7 @@ dependencies: repository: "file://charts/team-role-and-bindings" condition: team-role-and-bindings.enabled - name: hyperpod-inference-operator - version: "1.1.0" + version: "1.2.0" repository: "file://charts/inference-operator" condition: inferenceOperators.enabled - name: hyperpod-patching diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml index 7b4671c2..86e81948 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/Chart.yaml @@ -15,11 +15,11 @@ 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: 1.1.0 +version: 1.2.0 # This is the version number of the application being deployed. Keep this aligned # with operator image MAJOR.MINOR version. -appVersion: "2.1" +appVersion: "2.2" 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 7616f134..908fb9f8 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 @@ -1018,6 +1018,474 @@ spec: required: - name type: object + probes: + description: Configuration for container probes (liveness, readiness, + startup) + properties: + livenessProbe: + description: Liveness probe configuration + properties: + exec: + description: Exec specifies a command to execute in the + container. + properties: + command: + description: |- + Command is the command line to execute inside the container, the working directory for the + command is root ('/') in the container's filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use + a shell, you need to explicitly call out to that shell. + Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + x-kubernetes-list-type: atomic + type: object + failureThreshold: + description: |- + Minimum consecutive failures for the probe to be considered failed after having succeeded. + Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies a GRPC HealthCheckRequest. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + default: "" + description: |- + Service is the name of the service to place in the gRPC HealthCheckRequest + (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + + If this is not specified, the default behavior is defined by gRPC. + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies an HTTP GET request to + perform. + properties: + host: + description: |- + Host name to connect to, defaults to the pod IP. You probably want to set + "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: |- + The header field name. + This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + x-kubernetes-list-type: atomic + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Name or number of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: |- + Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: |- + Number of seconds after the container has started before liveness probes are initiated. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + periodSeconds: + description: |- + How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: |- + Minimum consecutive successes for the probe to be considered successful after having failed. + Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies a connection to a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Number or name of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: |- + Optional duration in seconds the pod needs to terminate gracefully upon probe failure. + The grace period is the duration in seconds after the processes running in the pod are sent + a termination signal and the time when the processes are forcibly halted with a kill signal. + Set this value longer than the expected cleanup time for your process. + If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this + value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates stop immediately via + the kill signal (no opportunity to shut down). + This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. + Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: |- + Number of seconds after which the probe times out. + Defaults to 1 second. Minimum value is 1. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + type: object + readinessProbe: + description: Readiness probe configuration. If not specified, + default values will be applied. + properties: + exec: + description: Exec specifies a command to execute in the + container. + properties: + command: + description: |- + Command is the command line to execute inside the container, the working directory for the + command is root ('/') in the container's filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use + a shell, you need to explicitly call out to that shell. + Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + x-kubernetes-list-type: atomic + type: object + failureThreshold: + description: |- + Minimum consecutive failures for the probe to be considered failed after having succeeded. + Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies a GRPC HealthCheckRequest. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + default: "" + description: |- + Service is the name of the service to place in the gRPC HealthCheckRequest + (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + + If this is not specified, the default behavior is defined by gRPC. + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies an HTTP GET request to + perform. + properties: + host: + description: |- + Host name to connect to, defaults to the pod IP. You probably want to set + "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: |- + The header field name. + This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + x-kubernetes-list-type: atomic + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Name or number of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: |- + Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: |- + Number of seconds after the container has started before liveness probes are initiated. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + periodSeconds: + description: |- + How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: |- + Minimum consecutive successes for the probe to be considered successful after having failed. + Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies a connection to a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Number or name of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: |- + Optional duration in seconds the pod needs to terminate gracefully upon probe failure. + The grace period is the duration in seconds after the processes running in the pod are sent + a termination signal and the time when the processes are forcibly halted with a kill signal. + Set this value longer than the expected cleanup time for your process. + If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this + value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates stop immediately via + the kill signal (no opportunity to shut down). + This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. + Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: |- + Number of seconds after which the probe times out. + Defaults to 1 second. Minimum value is 1. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + type: object + startupProbe: + description: Startup probe configuration + properties: + exec: + description: Exec specifies a command to execute in the + container. + properties: + command: + description: |- + Command is the command line to execute inside the container, the working directory for the + command is root ('/') in the container's filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use + a shell, you need to explicitly call out to that shell. + Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + x-kubernetes-list-type: atomic + type: object + failureThreshold: + description: |- + Minimum consecutive failures for the probe to be considered failed after having succeeded. + Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies a GRPC HealthCheckRequest. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + default: "" + description: |- + Service is the name of the service to place in the gRPC HealthCheckRequest + (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + + If this is not specified, the default behavior is defined by gRPC. + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies an HTTP GET request to + perform. + properties: + host: + description: |- + Host name to connect to, defaults to the pod IP. You probably want to set + "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: |- + The header field name. + This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + x-kubernetes-list-type: atomic + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Name or number of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: |- + Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: |- + Number of seconds after the container has started before liveness probes are initiated. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + periodSeconds: + description: |- + How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: |- + Minimum consecutive successes for the probe to be considered successful after having failed. + Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies a connection to a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: |- + Number or name of the port to access on the container. + Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: |- + Optional duration in seconds the pod needs to terminate gracefully upon probe failure. + The grace period is the duration in seconds after the processes running in the pod are sent + a termination signal and the time when the processes are forcibly halted with a kill signal. + Set this value longer than the expected cleanup time for your process. + If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this + value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates stop immediately via + the kill signal (no opportunity to shut down). + This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. + Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: |- + Number of seconds after which the probe times out. + Defaults to 1 second. Minimum value is 1. + More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes + format: int32 + type: integer + type: object + type: object resources: description: Defines the Resources in terms of CPU, GPU, Memory needed for the model to be deployed diff --git a/helm_chart/HyperPodHelmChart/charts/inference-operator/values.yaml b/helm_chart/HyperPodHelmChart/charts/inference-operator/values.yaml index 878fb183..48171a40 100644 --- a/helm_chart/HyperPodHelmChart/charts/inference-operator/values.yaml +++ b/helm_chart/HyperPodHelmChart/charts/inference-operator/values.yaml @@ -21,7 +21,7 @@ image: ap-southeast-4: 311141544681.dkr.ecr.ap-southeast-4.amazonaws.com ap-southeast-3: 158128612970.dkr.ecr.ap-southeast-3.amazonaws.com eu-south-2: 025050981094.dkr.ecr.eu-south-2.amazonaws.com - tag: v2.1 + tag: v2.2 pullPolicy: Always repository: hyperpodClusterArn: