Prerequisites

important

The installation process requires familiarity with Kubernetes and Helm.

Credentials

A user account with access to Aleph Alpha Artifactory. We will provide this to you.

On your local machine

note

The documentation assumes you are using Linux or macOS for your installation, but this is not a requirement.

Aspect	Requirements
Container Orchestration Platform	Kubernetes client v 1.29 and above • You can check this using kubectl version • Check your connectivity using kubectl get nodes
Package Manager	Helm v 3.0 and above • You can check this using helm version

On your Kubernetes Cluster

Aspect	Criteria	Minimum Requirements
Hardware	GPU	Minimal Setup: 2 GPUs (with MIG), 3 GPUs (without MIG) Recommended Setup: 6 GPUs (with MIG), 7 GPUs (without MIG) Note: Actual # of GPUs depends on models selected for deployment. Type: NVIDIA Ampere, Lovelace or Hopper generation. Currently, only NVIDIA GPUs are supported. Support for other vendors may be added in the future. GPU Nodes: Your Kubernetes cluster must include GPU nodes to run the inference stack application pods. During the finetuning of models, additional GPUs will be required. See Finetuning Service Resource Requirements
	CPU & Memory	24 CPU cores, 128 GB RAM The exact requirements will depend on the number of users as well as which components of the stack you intend to use. - Resource requirements DataPlatform & Document Index - Resource requirements PhariaAssistant
	Object Storage	Quantity: 3x Type: minio or any other S3 backend type for PhariaData and PhariaFinetuning Input & Output Operations (IOPS) maximum: 1000 or above Throughput maximum: 100 Mb/s or above
	Persistent Volumes	Persistent volumes accessible by all GPU nodes in the cluster are essential for storing model weights. Ensure your persistent volumes are configured to be accessible across availability zones if applicable in your environment.
Software	Networking	Installed in a single namespace with open communication between all services in the namespace
	NVIDIA GPU Operator	We strongly recommend using the NVIDIA GPU Operator v 24 and above on default settings to manage NVIDIA drivers and libraries on your GPU nodes. More details on the GPU Operator setup can be found at GPU Operator Setup.
	Ingress controller & domain	The cluster must include an ingress controller to enable external access to the PhariaAI service. A certificate manager must also be configured to support secure access via TLS (Transport Layer Security). A dedicated domain must be assigned to the Kubernetes cluster, enabling each service to host its application under a subdomain of this domain (e.g., https://<service-name>.<ingress-domain>).
	Relational Database Management	Postgres v 14.0 and above Quantity: 1x Large Storage: 800 GB CPU: 8x Memory: 16GB
	Network Access & Whitelisting	Not required if networking requirements are met. If you require multiple name spaces please discuss this with our Product Support team.
	Artifact Management	Ability to pull the Helm chart containing the pharia-ai-helm and container images from an external artifact repository manager, such as Jfrog. Credentials for this will be provided to you.
	Monitoring & Observability	No fixed requirements but we can recommend the use of Prometheus & Grafana.
	Cert manager	Cert Manager is required to provision webhook certs for Dynamic Model Management feature.
	ClusterRole	PhariaOS requires a ClusterRole for hardware discovery and model management. By default, the chart will create the necessary ClusterRole and ClusterRoleBinding. For detailed configuration, refer to PhariaOS Manager Settings and How to use existing cluster role.