Configuration

Configure workers on your engine.

Config file

The engine reads ~/.config/inferencesh/engine.yml (XDG config directory on Linux).

Legacy path /etc/inferencesh/engine.yml (used before engine v1.10.9) is migrated automatically on first start when the new file does not exist yet. Check engine logs for Migrated config from ... if you upgraded from an older install.

CLI credentials (infsh, belt) are stored separately in ~/.inferencesh/config.json — set your API key with infsh login or INFSH_API_KEY.

Print resolved paths (config, cache, logs):

1inference-engine config

1api_url: https://api.inference.sh2api_key: inf_your_key34name: my-server56workers:7  cpu:8    count: 29  gpu:10    - gpus: [0]11    - gpus: [1]

CPU workers

For tasks that don't need GPU:

1workers:2  cpu:3    count: 4

GPU-only engines do not get automatic CPU workers. The platform only defaults to two CPU workers when you have no GPU workers configured (pure CPU engine). If you run CPU-only apps on a GPU machine, set workers.cpu.count explicitly.

GPU workers

One worker per GPU:

1workers:2  gpu:3    - gpus: [0]4    - gpus: [1]5    - gpus: [2]

Multi-GPU workers

For large models needing multiple GPUs:

1workers:2  gpu:3    - gpus: [0, 1]  # Uses both

Engine name

1name: gpu-server-1

Shows in the workspace to identify this machine.

Runtime

Controls how workers are isolated on the host:

1runtime: docker   # default on Linux2runtime: bare     # default on macOS — native visor process, no Docker

When runtime is omitted, the engine picks bare on macOS and docker on Linux. Use bare on macOS for local development without a Docker daemon. Production Linux hosts should use docker.

After changes

Restart the engine:

1sudo systemctl restart inference-engine

Next

→ Using Private Workers