AI Agent Skills

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

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

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

NVIDIA device plugin for Kubernetes

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, t…

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

AI agent skills published by NVIDIA

AIStore: scalable storage for AI applications

The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the…

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Perception and AI components for autonomous mobile robotics.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…

DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).