Install with Docker

DeepLM Ops ships as a Docker image. You need Docker with at least 8 GB of memory. The first start downloads the model once (2.55 GiB).

Pick your system

The same steps everywhere

Once Docker is installed, the steps are identical on every system.

1. Get access

Accept the DeepLM GitHub org invite if you received one, then create a classic token with only read:packages. The full steps are in Create your GitHub token.

docker login ghcr.io -u <your-github-username>

Paste the token at the Password prompt.

2. Pull the image

Docker picks the right build for your machine. Intel and AMD machines get amd64, which can use an NVIDIA GPU. Apple silicon and other Arm machines get a CPU-only arm64 build.

docker pull ghcr.io/deeplm/dlm-ops-dev:0.1.1

3. Run it

This is one line and works in macOS and Linux shells and in PowerShell. The -e DLM_OPS_SLURM=replay flag turns on the demo cluster. Remove it to ask about your own machine.

docker run -d --name dlm-ops -p 127.0.0.1:8090:8090 -v dlm-ops:/var/lib/dlm-ops --read-only --tmpfs /tmp --tmpfs "/run/dlm:uid=1000,gid=1000,mode=0700" --cap-drop ALL --security-opt no-new-privileges --pids-limit 256 --restart unless-stopped -e DLM_OPS_SLURM=replay ghcr.io/deeplm/dlm-ops-dev:0.1.1

To use an NVIDIA GPU, add --gpus all right after docker run -d. See Use an NVIDIA GPU.

4. Sign in

Wait until the logs say "model ready", then open the link that contains the token.

docker logs dlm-ops

Stop it

docker rm -f dlm-ops

The model lives in a Docker volume, so docker volume rm dlm-ops also deletes the downloaded model.