GPU Access

GPU Access

The gpu entitlement exposes the host GPU to your app for CUDA, ML inference, image processing, DeepStream, PyTorch, TensorRT, and MLX workloads. WendyOS does not expose GPU devices to apps unless the app declares the entitlement.

Today this covers NVIDIA GPUs (CUDA) — both NVIDIA Jetson devices and x86 Intel/AMD machines with an NVIDIA card. AMD GPU acceleration via ROCm is in progress.

Add the entitlement from your project directory:

wendy project entitlements add gpu

Inspect GPU Capabilities

Check the target device version and hardware summary:

wendy device version

For a focused hardware capability view:

wendy device hardware list --category gpu

The output reports GPU-related device paths and properties when the target exposes them.

Common Pairings

GPU apps often also need:

• camera for computer vision and live inference
• network for inference APIs or dashboards
• audio for voice AI pipelines
• persist for model caches and local output

For camera inference:

wendy project entitlements add camera
wendy project entitlements add gpu

For a networked inference server:

wendy project entitlements add gpu
wendy project entitlements add network --mode host

App Configuration

A minimal GPU app uses:

{
  "appId": "com.example.gpu",
  "platform": "linux",
  "version": "1.0.0",
  "entitlements": [
    { "type": "gpu" }
  ]
}

Then deploy:

wendy run

Raspberry Pi Board Telemetry

On Raspberry Pi hosts, the gpu entitlement also exposes the VideoCore mailbox device (/dev/vcio). This lets your app read board telemetry — power, voltage and current, temperature, throttling state, and (on Raspberry Pi 5) the PMIC ADC channels — through the firmware property interface, the same channel the vcgencmd tool uses.

This is added only on Raspberry Pi hardware, and only when the /dev/vcio node is present. On NVIDIA Jetson devices the entitlement grants the CUDA/CDI access described above instead — the VideoCore mailbox is not exposed there — and on hardware that is neither, it has no effect.

{
  "appId": "com.example.power-monitor",
  "platform": "linux",
  "version": "1.0.0",
  "entitlements": [
    { "type": "gpu" }
  ]
}