Install on Windows

This guide installs Docker Desktop on Windows 10 or 11 and runs DeepLM Ops from PowerShell. You need at least 8 GB of memory available to Docker, and virtualization turned on in your BIOS.

1. Install WSL 2

Docker Desktop uses WSL 2 on Windows. Open PowerShell as Administrator and run:

wsl --install

Restart your PC when it finishes.

2. Install Docker Desktop

In PowerShell:

winget install -e --id Docker.DockerDesktop

You can also download the installer from the Docker website. Start Docker Desktop once after installing and accept the terms. Keep the WSL 2 based engine turned on, which is the default.

3. Give Docker 8 GB of memory

With WSL 2, Docker gets half of your PC's RAM by default. If that is less than 8 GB, raise it. The steps are in Give Docker enough memory.

4. Check that Docker works

docker --version
docker run --rm hello-world

5. Log in to the image registry

Accept the DeepLM GitHub org invite, then create a classic token with only read:packages. See Create your GitHub token.

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

Paste the token at the Password prompt.

6. Pull the image

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

7. Run it

This command is one line and works as is in PowerShell. It starts the demo cluster, a sample campus cluster with made-up jobs.

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 ask about your own machine instead, run it without -e DLM_OPS_SLURM=replay.

With an NVIDIA GPU

Windows needs Docker Desktop with WSL 2 and an up-to-date NVIDIA driver installed on Windows. Add --gpus all right after docker run -d:

docker run -d --gpus all --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

8. Open the chat page

Wait until the logs say "model ready". The first start downloads the model once (2.55 GiB).

docker logs dlm-ops

Open the http://127.0.0.1:8090/#token=... link in your browser.

Stop it

docker rm -f dlm-ops

Next steps

Try the sample questions, or see Common problems if something does not work.