Hosters

Hoster Overview

How to connect your GPU server to Qudata.ai and start renting out capacity.

Qudata Agent is installed on your server and turns it into a Qudata.ai marketplace node. After installation, the platform handles task execution automatically - you only need to keep the node available.

How it works

Each user task runs inside an isolated virtual machine.

Virtualization uses QEMU/KVM, and GPU is passed into VM using hardware PCI passthrough via VFIO.

Users get near-native hardware performance, while hosters cannot access task content.

You do not need NVIDIA drivers on host OS - drivers are installed automatically only inside VM.

How to become a hoster

  1. Ensure server matches requirements.
  2. Run installer with your API key.
  3. After installation, your node appears in marketplace.
wget -qO- https://agent.qudata.ai/install.sh | sudo bash -s -- ak-YOUR-API-KEY

You can get API key in dashboard: qudata.ai/profile/hosts.

Server requirements

ParameterRequirement
OSUbuntu 22.04+
GPUNVIDIA (without host drivers)
BIOSVT-d / AMD-Vi enabled
RAMfrom 8 GB
Diskfrom 50 GB free
Accessroot

Installation flow

Installation runs in two stages.

Stage 1 - Host preparation

  • Detect GPU and verify compatibility.
  • Verify no NVIDIA drivers on host.
  • Configure GPU isolation (IOMMU/VFIO) and install required components.
  • Reboot if IOMMU was not enabled before.

Stage 2 - Launch

  • Download VM image.
  • Run GPU passthrough test to verify transfer into VM.
  • Start Agent as a system service.

After successful completion, node is registered on platform automatically.

On this page