PyG Release 25.03

This PyG container release is intended for use on the NVIDIA® Hopper Architecture GPU, NVIDIA H100, the NVIDIA® Ampere Architecture GPU, NVIDIA A100, and the associated NVIDIA CUDA® 12 and NVIDIA cuDNN 9 libraries.

Driver Requirements

Release 25.03 is based on CUDA 12.8.1.010 which requires NVIDIA Driver release 570 or later. However, if you are running on a data center GPU (for example, B100, L40, or any other data center GPU), you can use NVIDIA driver release 470.57 (or later R470), 525.85 (or later R525), 535.86 (or later R535), or 550.54 (or later R550) in forward-compatibility mode.

The CUDA driver's compatibility package only supports particular drivers. Thus, users should upgrade from all R418, R440, R450, R460, R510, R520, R530, R545 and R555 and R560 drivers, which are not forward-compatible with CUDA 12.8. For a complete list of supported drivers, see the CUDA Application Compatibility topic. For more information, see CUDA Compatibility and Upgrades.

Contents of the PyG container

This container image includes the complete source of the NVIDIA version of PyG in /opt/pyg/pytorch_geometric. It is prebuilt and installed as a system Python module. The /workspace/examples folder is copied from /opt/pyg/pytorch_geometric/examples for users starting to run PyG. For example, to run the gcn.py example:

            

            
/workspace/examples# python gcn.py
        

See /workspace/README.md for details.

The container also includes the following:

• torch-geometric 2.7.0
• pyg-lib 0.4.0
• Built on PyTorch 25.03, which contains the following:
  • Ubuntu 24.04 including Python 3.12
  • NVIDIA CUDA 12.8.1.012
  • NVIDIA cuBLAS 12.8.4.1
  • NVIDIA cuDNN 9.8.0.87
  • NVIDIA NCCL 2.25.1
  • NVIDIA RAPIDS™ 25.02
  • Apex
  • rdma-core 50.0
  • NVIDIA HPC-X 2.21
  • OpenMPI 4.1.7
  • GDRCopy 2.4.1
  • TensorBoard 2.9.0
  • Nsight Compute 2025.1.1.2
  • Nsight Systems 2025.1.1.110
  • NVIDIA TensorRT™ 10.9.0.34
  • Torch-TensorRT 2.7.0a0
  • NVIDIA DALI® 1.47
  • MAGMA 2.6.2
  • JupyterLab 4.2.5 including Jupyter-TensorBoard
  • TransformerEngine v2.1
  • PyTorch quantization wheel 2.1.2

GPU Requirements

Release 25.03 supports CUDA compute capability 6.0 and later. This corresponds to GPUs in the NVIDIA Pascal, NVIDIA Volta™, NVIDIA Turing™, NVIDIA Ampere architecture, and NVIDIA Hopper™ architecture families. For a list of GPUs to which this compute capability corresponds, see CUDA GPUs. For additional support details, see Deep Learning Frameworks Support Matrix.

Key Features and Enhancements

• The latest GNN+LLM features. See /workspace/examples/llm/README.md for details.
• Heterogeneous Link prediction with CuGraph. See examples/multi_gpu/README.md.
• New tutorial for GraphTransformers: https://pytorch-geometric.readthedocs.io/en/latest/tutorial/graph_transformer.html

Announcements

• None.

NVIDIA PyG Container Versions

The PyG container supports the same version of Ubuntu and CUDA as the PyTorch container.

Known Issues

• None.