CUDA
CUDA is NVIDIA's parallel computing platform and programming model for running general-purpose computations on its GPUs.
CUDA is a parallel computing platform and programming model that NVIDIA announced in 2006. It lets developers use GPUs, originally built for graphics, for general-purpose computation by writing GPU code in languages such as C and C++. CUDA runs only on NVIDIA GPUs.
NVIDIA provides libraries built on CUDA, including cuDNN for deep learning and cuBLAS for linear algebra. Major deep learning frameworks such as PyTorch and TensorFlow rely on CUDA to train and run models on NVIDIA GPUs.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
…unPod handles the container packaging rather than requiring developers to write a Dockerfile, match CUDA components, and repeatedly push large container images.