CuDNN — CUDA Deep Neural Network Library

Fact

NVIDIA’s low-level GPU library for speeding up deep learning.

In Plain Words

cuDNN is a pit crew for deep learning. When the model pulls in, the heavy tire-change jobs happen fast.

It speeds up training and prediction under the hood. You often meet it hidden inside PyTorch and vision models.

Related Concepts

• Compute Unified Device Architecture
• PyTorch Deep Learning Framework
• Convolutional Neural Network
• GPU Compute

CUDA
cuDNN is built on CUDA and uses it to run deep learning work faster.

PyTorch
PyTorch often calls cuDNN under the hood for GPU speed.

CNN
cuDNN speeds up the convolution and activation steps in CNNs.

GPU
cuDNN needs a GPU, because it helps the GPU handle heavy work.