PyG Release 26.03

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 26.03 is based on CUDA 13.2.0. For comprehensive and up-to-date driver compatibility information, please refer to the following documentation:

• NVIDIA CUDA Compatibility Guide - Compati.bility information between CUDA versions and driver releases.
• CUDA Toolkit Release Notes - Driver version requirements and compatibility matrices.
• NVIDIA Drivers Download - Latest NVIDIA drivers.

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 2.8.0
• pyg-lib 0.6.0
• Built on PyTorch 26.03, which contains the following:
  • Ubuntu 24.04 including Python 3.12
  • NVIDIA CUDA 13.2.0.046
  • NVIDIA cuBLAS 13.3.0.5
  • NVIDIA cuDNN 9.20.0.48
  • NVIDIA NCCL 2.29.7
  • NVIDIA RAPIDS™ 25.10
  • Apex
  • rdma-core 50.0
  • NVIDIA HPC-X 2.26
  • OpenMPI 4.1.7
  • GDRCopy 2.4.1
  • TensorBoard 2.9.0
  • Nsight Compute 2026.1.0.9
  • Nsight Systems 2026.1.2.63
  • NVIDIA TensorRT™ 10.16.0.72
  • Torch-TensorRT 2.11.0a0
  • NVIDIA DALI® 2.0
  • MAGMA 2.6.2
  • JupyterLab 4.2.5 including Jupyter-TensorBoard
  • TransformerEngine v2.13
  • PyTorch quantization wheel 2.1.2

GPU Requirements

Release 26.03 supports CUDA compute capability 6.0 and later. This corresponds to GPUs in the NVIDIA Ampere architecture, NVIDIA Hopper™, and NVIDIA Blackwell 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.

• Continued optimizations and stability improvements for GNN+LLM

Announcements

• None.

NVIDIA PyG Container Versions

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

Known Issues

• Please refer to the CUDA DL Release Notes for additional details.