Your first node.
A clear path forward.

Start with the right foundation.

Use a Linux host with Docker Engine and Compose, compatible GPU drivers, and enough memory and storage for your selected model.

• A supported runtime and GPU combination.
• Persistent directories for configuration and model storage.
• Access to the Helm Node container package and matching release deployment files.

Validate your configuration.

Use the Intel SYCL or NVIDIA CUDA Compose file supplied with your release. Configure model storage, runtime images, device access and persistent configuration before starting.

docker compose config --quiet
docker compose pull
docker compose up -d
docker compose logs --tail=50 local-service

These commands assume your supplied file is named compose.yaml. Private packages require authorized registry access.

Make this node yours.

Open the service at its configured local address or through an SSH tunnel. Use the first-use setup token from the container logs to create your administrator account.

Select the GPUs the service may use, verify the configured model directory and keep a backup of your configuration. Configuration exports do not contain model weights.

From model to endpoint.

1. Register a model. Add a supported model from mounted storage or use the model transfer tools.
2. Create a profile. Select the engine, GPU placement, context length and concurrency.
3. Start and verify. Check readiness and logs before connecting an application.
4. Connect securely. Create a scoped inference token and use the URL in Connections.

llama.cpp is the default engine. vLLM requires a separate controller and supported recipes. Model registration alone does not establish runtime compatibility.

Bring enrollment into view.

Sign in to Helm Control with an email code, create or select your organization, and prepare a node enrollment package. In Helm Node, use Settings to activate the package.

Helm Fleet then provides a read-only view of registration, licensing allowance and audit activity. Remote orchestration and cloud-provider integrations are planned.