NVIDIA GitHub ↗

Repos

k8s-test-infra Go 12 stars done

K8s-test-infra

141 merged PRs · avg 9 days · fastest 0m
VideoProcessingFramework C++ 1.4k stars done

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

90 merged PRs · avg 7 days · fastest 0m
TensorRT C++ 12.7k stars error

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

cutlass C++ 9.3k stars error

CUDA Templates and Python DSLs for High-Performance Linear Algebra

apex Python 8.9k stars error

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

cuda-samples C 8.9k stars error

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

vid2vid Python 8.7k stars error

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Cosmos 8.1k stars error

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

garak HTML 7.0k stars error

the LLM vulnerability scanner

pix2pixHD Python 7.0k stars error

Synthesizing and manipulating 2048x1024 images with conditional GANs

FasterTransformer C++ 6.4k stars error

Transformer related optimization, including BERT, GPT

warp Python 6.2k stars error

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

Isaac-GR00T Jupyter Notebook 6.2k stars error

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

personaplex Python 5.5k stars error

PersonaPlex code.

tacotron2 Jupyter Notebook 5.3k stars error

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Megatron-LM Python 15.3k stars error

Ongoing research training transformer models at scale

FastPhotoStyle Python 11.2k stars error

Style transfer, deep learning, feature transform

DeepLearningExamples Jupyter Notebook 14.7k stars error

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

nvidia-docker 17.5k stars error

Build and run Docker containers leveraging NVIDIA GPUs

TensorRT-LLM Python 12.9k stars error

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

open-gpu-kernel-modules C 16.7k stars error

NVIDIA Linux open GPU kernel module source