Open-source library for scalable, reproducible evaluation of AI models and benchmarks.

A Datacenter Scale Distributed Inference Serving Framework

CUDA Python: Performance meets Productivity

No-GIL Python environment featuring NVIDIA Deep Learning libraries.

NVIDIA Math Libraries for the Python Ecosystem

Megatron's multi-modal data loader

A Python framework for accelerated simulation, data generation and spatial computing.

Modern C++ Programming Course (C++03/11/14/17/20/23/26)

A nvImageCodec library of GPU- and CPU- accelerated codecs featuring a unified interface

Multidimentional histogram calculation using CUDA C++

3rd party dependencies for DALI project

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

Repository for nvCOMP docs and examples. nvCOMP is a library for fast lossless compression/decompression on the GPU that can be downloaded from https://developer.nvidia.com/nvcomp.

NVIDIA Federated Learning Application Runtime Environment

AIStore: scalable storage for AI applications

Disables the WYSIWYG editor in Slack.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

A logging tool for deep learning.

Template-based FFT, optimized for x86 processors.