cuDNN
Description
The NVIDIA CUDA Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks.
More information
- Homepage: https://developer.nvidia.com/cudnn
Available Versions of cuDNN
Version | Module | Available on |
---|---|---|
8.9.4.25-CUDA-12.1.0 | numlib/cuDNN/8.9.4.25-CUDA-12.1.0 | Noctua 2 |
8.9.2.26-CUDA-12.1.1 | numlib/cuDNN/8.9.2.26-CUDA-12.1.1 | Noctua 2 |
8.8.0.121-CUDA-12.0.0 | numlib/cuDNN/8.8.0.121-CUDA-12.0.0 | Noctua 1 |
8.7.0.84-CUDA-11.8.0 | numlib/cuDNN/8.7.0.84-CUDA-11.8.0 | Noctua 1 |
8.4.1.50-CUDA-11.7.0 | numlib/cuDNN/8.4.1.50-CUDA-11.7.0 | Noctua 1, Noctua 2 |
8.3.0.98-CUDA-11.5.1 | numlib/cuDNN/8.3.0.98-CUDA-11.5.1 | Noctua 2 |
8.2.1.32-CUDA-11.3.1 | numlib/cuDNN/8.2.1.32-CUDA-11.3.1 | Noctua 2 |
8.0.4.30-CUDA-11.1.1 | numlib/cuDNN/8.0.4.30-CUDA-11.1.1 | Noctua 1, Noctua 2 |
7.4.2.24-CUDA-10.0.130 | numlib/cuDNN/7.4.2.24-CUDA-10.0.130 | Noctua 2 |
This table is generated automatically. If you need other versions please click pc2-support@uni-paderborn.de.
Usage Hints for cuDNN
If you need support in using this software or example job scipts please contact pc2-support@uni-paderborn.de.