System requirements

Related topics

Before you deploy BMC AMI Platform, make sure that your environment meets the recommended hardware requirements, cluster architecture, and networking specifications. This topic includes system requirements for an RKE2 Kubernetes cluster, recommendations, and deployment prerequisites.

Best practice

We recommend that you use the configuration options described in this topic for best performance and LLM outputs.

System requirementsEdit

You can deploy BMC AMI Platform on an RKE2 Kubernetes cluster.

Cluster topology guidelines

The following table displays recommendations for Control Plane and Worker nodes:

Node type	Requirement
Control Plane	Deployment: Must be deployed across at least two Availability Zones Role duality: Can perform dual roles (manager and worker), but this is not recommended for performance-critical environments Recommendation: Isolate control plane functions from workload run for optimal performance and stability
Worker	Overprovisioning: Additional 20–30 percent computing capacity to support: Rolling updates Node failure or eviction scenarios Deployment: Must be distributed across multiple Availability Zones for fault tolerance and service continuity Scalability: Cluster should support horizontal scaling based on workload demands

Recommended cluster topologies

For availability and workload handling, RKE2 Kubernetes is required as follows:

A minimum of three Control Planes
A minimum of three Worker nodes

Node sizing guidelines

The following table displays the node sizing requirements:

Node type

Component

Requirement

Control Plane

CPU

16+ cores (modern x86-64 or ARM architecture)

RAM

48+ GB (for application requirements)

Storage

Minimum 200-GB SSD with high IOPS and container storage

Worker

CPU

16+ cores (to handle container workloads)

RAM

48+ GB (depends on container memory requirements)

Storage

200+ GB SSD (based on container requirements)

LLM GPU

GPU-specific hardware and cloud requirements for the Recommended configuration option:

Supported LLM	Meta-Llama-3.1-8B-instruct 4K Quantized Granite-3.1-8B-Instruct Mixtral8x7b-instruct Quantized
On-premises hardware	GPU memory: 36 GB GPU: NVIDIA 4 × A10G or 1 × A100
AWS	g5.12xlarge (4 × A10G)
Azure	Standard_NC24ads_A100_v4 (1 × A100)

Software requirementsEdit

The following table displays the software requirements for RKE2 Kubernetes:

Component	Requirement
OS	Ubuntu LTS 24.04 or RHEL
Python	Version 3.x
Ansible	Latest version
Docker Engine	Latest stable version (minimum 28.0.x)
Helm	Version 3.6
NVIDIA GPU operator	Latest version

Storage requirements

The following table displays the storage requirements for RKE2 Kubernetes:

Platform	Requirements
RKE2 Kubernetes version 1.33.5	Requires an NFS server with a pre-created export folder with a size of at least 1 TB.
RKE2 Kubernetes version 1.33.5	Warning Important Make sure that NFS is reachable from all cluster nodes. Directory permissions must allow service write access (UID/GID 1000 or 0777). During installation, provide: NFS server (host or IP) NFS export path Local mount path (for example, /mnt/nfs/data)

SSH accessibility requirements

To deploy the LLM model from the UI, the system must securely connect to the master node where the model is installed and configured.
The provided PEM (SSH private key) enables this secure, authenticated connection, allowing the deployment process to transfer files, run setup commands, and complete the installation safely and automatically.

Important

The SSH key must belong to a user who has sufficient permissions to run kubectl commands on the Kubernetes cluster.

Example for creating and configuring the SSH key

Generate a new RSA private key in PEM format:
ssh-keygen -t rsa -b 4096 -m PEM -f aikey.pem
Add the public key to the authorized keys of the target user:
cat $KEY_PATH/aikey.pem.pub >> /root/.ssh/authorized_keys

Cluster-wide configuration

The public key created as a part of the SSH accessibility requirement must be added to the authorized_keys file on all nodes in the cluster.

Example for configuration

Copy the public key to each node.
Run the following command on every node:
cat $KEY_PATH/aikey.pem.pub >> /root/.ssh/authorized_keys

SSL and TLS requirements

To enable HTTPS communication for the web application, you must provide your own SSL and TLS certificate and private key. Place both files in the prerequisites directory on the master node before running the Ansible script. While running, the Ansible script prompts you to provide the paths to the certificate and key files.

You can use certificates issued by your organization’s Certificate Authority (CA).

Infrastructure and security requirementsEdit

The following table displays the infrastructure and security requirements for RKE2 Kubernetes:

Requirement	Details
Registry access	All nodes must access your container registry.
Ansible and Python	The Control Plane or Manager node must have Python 3.x and Ansible installed.

Important

If you are running on cloud with a load balancer, set Connection Idle Timeout to 1800 seconds (30 minutes) to match the AI external proxy timeout.

Supported versions for CES, BMC AMI DevX Code Insights, and BMC AMI DevX Workbench for VS Code products for Code ExplainEdit

The following table outlines the supported versions for the Code Explain feature across CES, Workbench for Eclipse and Code Insights, and Workbench for VS Code products.

BMC AMI Platform	CES	Workbench for Eclipse/Code Insights	Workbench for VS Code
2.0	23.04.02 or later	23.07.07 and 25.02.02	25.10.10 or later
1.6	23.04.02 or later	23.07.03 or later	24.04.1 or later
1.4	23.04.02 or later	23.06.01 or later	24.04.0 or later