CXL Distributed Operating System

Experimental WASM Microkernel Operating System

NVIDIA vGPU Device Manager manages NVIDIA vGPU devices on top of Kubernetes

The NVIDIA Driver Manager is a Kubernetes component which assist in seamless upgrades of NVIDIA Driver on each node of the cluster.

An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.

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

A toolkit for discovering cluster network topology.

CUDA Python: Performance meets Productivity

AIStore: scalable storage for AI applications

GPU accelerated decision optimization

Julia ports of the Rodinia benchmark suite for heterogeneous computing infrastructures

Rodinia benchmark

CXL remote offloading data movement aware compiler

Asterinas is a secure, fast, and general-purpose OS kernel, written in Rust and providing Linux-compatible ABI.

AMD SMI

GPGPU processor supporting RISCV-V extension, developed with Chisel HDL

Mirror of official Lustre development repository http://git.whamcloud.com/

This is a Chinese translation of the CUDA programming guide

Sniff CUDA ioctls

PTX on XPUs

NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer

HIP: C++ Heterogeneous-Compute Interface for Portability

Device-plugin for volcano vgpu which support hard resource isolation

HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container

ARM Architecture文档

Linux驱动，内核经典书籍

A machine learning accelerator core designed for energy-efficient AI at the edge.

NVIDIA GPUDirect Storage Driver

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmer…