For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

PyTorch 2.10.0 on AMD ROCm 7.2.4

This 1-Click image ships PyTorch 2.10.0, the widely used deep learning framework, running on an AMD ROCm 7.2.4 host stack on Ubuntu 24.04. It is preconfigured for AMD Instinct GPUs and packaged as a ready-to-run Docker container with PyTorch and its ROCm-accelerated libraries, alongside a JupyterLab environment with example notebooks.

PyTorch on ROCm provides a familiar eager-mode and compiled (torch.compile) experience with native AMD GPU acceleration for training and inference.

Software Included

Deploying this Offering using the Control Panel

Click the Deploy to DigitalOcean button to deploy this offering. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

[](https://cloud.digitalocean.com/gpus/new?appId=7978b6d9303899f6aba2b4fe&image=PyTorch 2.10.0 (ROCm 7.2.4) 2.10.0 on Ubuntu 24.04&type=applications)

Getting Started After Deploying PyTorch 2.10.0 (ROCm 7.2.4)

After the droplet boots, SSH in as root. The Jupyter Lab URL and token, plus the commands to start and inspect the PyTorch container, are printed in the login MOTD. PyTorch runs inside a Docker container; use the printed docker exec command to open an interactive shell, then python -c "import torch; print(torch.cuda.is_available())". Verify the GPU stack with amd-smi and rocminfo.