NVIDIA Vector - Moozonian

GitHub Repo https://github.com/5had3z/CerberusNet

5had3z/CerberusNet

The aim of this project is to generate a pointcloud with motion vectors and semantic segmentation of stereoscopic image sequences. Targeting real-time deployment on an nVIDIA Xavier.

GitHub Repo https://github.com/srvm/multi_device_vector

srvm/multi_device_vector

Vector type that spans multiple NVIDIA GPUs

GitHub Repo https://github.com/pnnl/s-blas

This package includes the implementation for four sparse linear algebra kernels: Sparse-Matrix-Vector-Multiplication (SpMV), Sparse-Triangular-Solve (SpTRSV), Sparse-Matrix-Transposition (SpTrans) and Sparse-Matrix-Matrix-Multiplication (SpMM) for Single-node Multi-GPU (scale-up) platforms such as NVIDIA DGX-1 and DGX-2.

GitHub Repo https://github.com/NVIDIA/NVIDIAOpticalFlowSDK

NVIDIA/NVIDIAOpticalFlowSDK

Optical Flow SDK exposes the latest hardware capability of Turing GPUs dedicated to computing the relative motion of pixels between images. The hardware uses sophisticated algorithms to yield highly accurate flow vectors, with robust frame-to-frame intensity variations and tracks the true object motion faster and more accurately.

GitHub Repo https://github.com/timocafe/vector

timocafe/vector

Simple heterogenous vector class for CPU and Nvidia GPU.

GitHub Repo https://github.com/Bruce-Lee-LY/cuda_hgemv

Bruce-Lee-LY/cuda_hgemv

Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

GitHub Repo https://github.com/afanasyev-ilya/VectorGraphLibrary

afanasyev-ilya/VectorGraphLibrary

VGL is a high-performance graph processing framework, designed for modern NEC SX-Aurora TSUBASA vector architecture. VGL significantly outperforms many state-of the art graph-processing frameworks for modern multicore CPUs and NVIDIA GPUs, such as Gunrock, CuSHA, Ligra, Galois, GAPBS.

GitHub Repo https://github.com/JacopoPan/a-minimalist-guide

JacopoPan/a-minimalist-guide

Walkthroughs for DSL, AirSim, the Vector Institute, and more

GitHub Repo https://github.com/Aaryan-Kapoor/NvidiaOmniEmbed

Aaryan-Kapoor/NvidiaOmniEmbed

A local, multimodal embedding server and vector database using NVIDIA's Omni-Embed-Nemotron-3B. This project allows you to generate embeddings for Text, Images, Audio, and Video on consumer hardware (tested on RTX 5070 Ti / 12GB VRAM), save them to a local index, and perform multimodal semantic search.

GitHub Repo https://github.com/uuudown/S-BLAS

uuudown/S-BLAS

This package includes the implementation for Sparse-Matrix-Vector-Multiplication (SpMV) and Sparse-Matrix-Matrix-Multiplication (SpMM) for Single-node Multi-GPU (scale-up) platforms such as NVIDIA DGX-1 and DGX-2.