Getting Started
Pre-requisites
Kubernetes cluster
Prometheus monitoring system (if using autoscaling or rate limiting)
KEDA (Kubernetes Event-Driven Autoscaling) (if using autoscaling)
Installation
Create a values file with your configuration.
Modify the following command to install the chart at your cluster:
helm repo add supersonic https://fastmachinelearning.org/SuperSONIC helm repo update helm install <release-name> supersonic/supersonic --values <your-values.yaml> -n <namespace>Use a unique meaningful lowercase value as <release-name>, for example
supersonic-cms-run3
. This value will be used as a prefix for all resources created by the chart, unlessnameOverride
is specified in the values file.
Uninstall SuperSONIC
helm uninstall <release-name> -n <namespace>
Architecture
The SuperSONIC Helm chart will install components depicted at the diagram below, excluding Prometheus server and model repository, which must be connected by specifying relevant parameters in configuration file (see configuration guide).
The KEDA autoscaler can be enabled/disabled via the
autoscaler.enabled
parameter.