Skip to content

GPU and CUDA

An NVIDIA GPU is optional but strongly recommended.

The installer asks whether to install with CUDA support. Without a GPU, model inference and training fall back to the CPU — they still work, but not at a speed that supports iterating.

Task Without a GPU
Interactive prompting usable, but slow enough to interrupt your flow
Batch inference feasible for small datasets, painful for large ones
Training impractical

Requirements

  • an NVIDIA GPU with current drivers
  • CUDA support selected during installation

To change this later:

./install.sh --reconfigure

Checking it is being used

If inference is far slower than expected, check the AI service's log:

./iquana.sh logs ai-service

A service that fell back to the CPU says so at startup.

uv 0.10 or newer is required for the CUDA wheels

Older versions reject the PyTorch wheels the AI service needs. Run uv self update if the installer complains.