The NVIDIA TensorRT RTX Execution Provider (EP) is an inference deployment solution designed specifically for NVIDIA RTX GPUs, optimized for client-centric use cases.

NVIDIA FastGen: Fast Generation from Diffusion Models

MLPerf Client is a benchmark for Windows, Linux and macOS, focusing on client form factors in ML inference scenarios.

Official inference repo for FLUX.1 models

Tool to statically recompile N64 games into native executables

Generative AI extensions for onnxruntime

Simple Onnxruntime DML test

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Official Code for Stable Cascade

Tensor library for machine learning

Video processing in Python

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

Decompilation of The Legend of Zelda: The Wind Waker

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

TensorRT Extension for Stable Diffusion Web UI

ONNX-TensorRT: TensorRT backend for ONNX

The Free and Open Source Cross Platform YUV Viewer with an advanced analytics toolset

Stable Diffusion web UI

top #1 and most feature rich GPT wrapper for git — generate commit messages with an LLM in 1 sec — works with Claude, GPT and every other provider, supports local Ollama models too

Sample showing OpenGL and CUDA interop

C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

GGRS is a reimagination of GGPO, enabling P2P rollback networking in Rust. Rollback to the future!

CUDA Kernel Benchmarking Library

A VSCode extension that allows you to use ChatGPT

AI-related samples made available by the DevTech ProViz team

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

Extended and advanced applications to the Rivermax SDK (Networking SDK for Media and Data Streaming).