Overview

Clusters are running container instances. You can pull an instance from a container registry such as Docker Hub, GitHub Container Registry, Amazon Elastic Container Registry, or another compatible registry.

Note When building an image for Tensor One, use the flag --platform linux/amd64,linux/arm64 to ensure your image is compatible with the platform.

Understanding Clusters components and configuration

A Cluster is a server container created by you to access the hardware, with a dynamically generated assigned identifier. For example, 2s56cp0pof1rmt identifies the instance.

A Cluster comprises a container volume with the operating system and temporary storage, a disk volume for permanent storage, an Ubuntu Linux container, allocated vCPU and system RAM, GPUs or CPUs for specific workloads, a pre-configured template for easy software access, and a proxy connection for web access.

Each Clusters encompasses a variety of components:

• A container volume that houses the operating system and temporary storage.
  • This storage is volatile and will be lost if the Clusters is halted or rebooted.
• A disk volume for permanent storage, preserved for the duration of the Cluster's lease, akin to a hard disk.
  • This storage is persistent and will be available even if the Cluster is halted or rebooted.
• An Ubuntu Linux container, capable of running almost any software that can be executed on Ubuntu.
• Assigned vCPU and system RAM dedicated to the container and any processes it runs.
• Optional GPUs or CPUs, tailored for specific workloads like CUDA or AI/ML tasks, though not mandatory for starting the container.
• A pre-configured template that automates the installation of software and settings upon Cluster creation, offering straightforward, one-click access to various packages.
• A proxy connection for web access, allowing connectivity to any open port on the container.
  • For example, https://[Cluster-id]-[port number].proxy.tpu.one, or https://2s56cp0pof1rmt-7860.proxy.tpu.one/).

Learn more

You can jump straight to a running Cluster by starting from a template. For more customization, you can configure the following:

• GPU Type and Quantity
• System Disk Size
• Start Command
• Environment Variables
• Expose HTTP/TCP ports
• Persistent Storage Options

To get started, see how to Choose a Cluster then see the instructions on Manage Clusters.