Creating an EC2 instance
Before you begin
The following infrastructure is required for optimal performance with BMC AMI AI Services.
Configuration option | Supported LLM | AWS |
---|---|---|
Recommended |
| g5.12xlarge |
If you don't already have them, create a Virtual Private Cloud (VPC), set up subnets, and configure an Internet Gateway as follows. If you already have them, you can reuse them later in the deployment process.
- Sign in to your AWS account.
Open the Amazon VPC console athttps://console.aws.amazon.com/vpcconsole.
- On the VPC console dashboard, click Create VPC .
- Keep all unspecified values at their default settings in the following steps.
- In the VPC settings field, click VPC and more.
- For ... name, enter a name such as BMC-AMI-AI-Services.
- Enter the IPv4 CIDR block value. For example, 10.0.0.0/16.
- For Number of private subnets, select 0 (zero).
- For VPC endpoints, select None.
- Click Create VPC.
To create an EC2 instance
- Sign in to your AWS account.
Open the Amazon EC2 console athttps://console.aws.amazon.com/ec2/ .
- On the EC2 console dashboard, in the Launch instance area, click Launch instance.
- In the Name field, in the Name and tags area, enter a name (for example, AMIAI_VM).
- In the search box in the Application and OS Images area, enter Deep Learning OSS Nvidia Driver AMI GPU PyTorch.
- From the search results, select Ubuntu/Deep Learning OSS Nvidia Driver AMI GPU PyTorch 2.2 or later (Ubuntu 22.04).
- In the Instance type area, from the menu, we recommend that you select g5.12xlarge for optimal performance.
- In the Key pair (login) area, click Create new key pair and follow these steps:
- Enter a key pair name (for example, AMIAI_KeyPair).
- Select RSA for the key pair type.
- Select .ppk for the Private Key file format.
- Click Create key pair to download the .ppk file. Store it in a safe location.
- In the Network settings area, click Edit.
- For VPC, select the VPC that you created in the previous step.
- From the Auto-assign public IP menu, select Enable.
- For Firewall, click Create security group.
- For Inbound Security Group Rules, delete all rules except for the SSH type.
- From the SSH Source type , select My IP . Only your machine has SSH access to this EC2 instance.
- In the Configure storage area, modify the storage in accordance with your needs.
- In the Summary area, enter the number of instances of EC2 required.
- Click Launch instance.
- On the confirmation page, which indicates that your instance is launching, click View all instances to close the confirmation page and return to the console.
- In the Instances area, you can view the launch status of your EC2 instance. Launching an instance takes a short time. When you launch an instance, its initial state is Pending. After the instance starts, its state changes to Running and receives a public DNS name.
- Click the Instance ID to launch your instance.
- Note down the Public and Private IPs and their DNS names.
To add the inbound rules, seehttps://docs.aws.amazon.com/finspace/latest/userguide/step5-config-inbound-rule.html.
- Add an inbound rule to the EC2 instance public IP address to allow traffic on port 8000.
- If you deployed the BMC AMI AI Services on zCX/zLinux, then add the inbound rule to the zCX/zLinux instance IP address to port 4000-4003.
- If the SSL is enabled, then add an inbound rule on ports 8000, 8001, 8002, 8080, 8005, and 4000-4003. You must allow these ports to the EC2 Instance public IP.
Where to go from here
Tip: For faster searching, add an asterisk to the end of your partial query. Example: cert*