OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Transformer related optimization, including BERT, GPT

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Fast inference engine for Transformer models

LightSeq: A High Performance Library for Sequence Processing and Generation

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Small C++ program to display images in a (modern) terminal using RGB ANSI codes and unicode block graphics characters

HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs