An open-source C++ library developed and used at Facebook.

An MCP-based chatbot | 一个基于MCP的聊天机器人

Seamless operability between C++11 and Python

Tensor library for machine learning

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

oneAPI Threading Building Blocks (oneTBB)

ArrayFire: a general purpose GPU library.

Lightning fast C++/CUDA neural network framework

HIP: C++ Heterogeneous-Compute Interface for Portability

A retargetable MLIR-based machine learning compiler and runtime toolkit.

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

CUDA Library Samples

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

CUDA Core Compute Libraries

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

A Python library transfers PyTorch tensors between CPU and NVMe

Optimized FP16/BF16 x FP4 GPU kernels for AMD GPUs

rocDecode is a high performance video decode SDK for AMD hardware

The C++ Standard Library for your entire system.

HIP Kernel Benchmarking Library

cuDNN samples v9.x