CUDA® is a parallel computing platform and programming model developed by NVIDIA for general computing on graphical processing units (GPUs). With CUDA, developers are able to dramatically speed up computing applications by harnessing the power of GPUs.
#大语言模型#A high-throughput and memory-efficient inference and serving engine for LLMs
#计算机科学#Instant neural graphics primitives: lightning fast NeRF and more
翻译 - 即时神经图形基元:闪电般快速的 NeRF 等
#计算机科学#Open3D: A Modern Library for 3D Data Processing
翻译 - Open3D:3D数据处理的现代库
#计算机科学#Containers for machine learning
#区块链#Modular ZK(Zero Knowledge) backend accelerated by GPU
#大语言模型#SGLang is a fast serving framework for large language models and vision language models.
CUDA 开发人员使用的示例,演示了 CUDA 工具包中的功能
#计算机科学#OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
翻译 - OneFlow是一个以性能为中心的开源深度学习框架。
#计算机科学#CUDA Templates for Linear Algebra Subroutines
翻译 - 用于线性代数子程序的 CUDA 模板
ALIEN is a CUDA-powered artificial life simulation program.
翻译 - ALiEn 是一款 GPU 加速的人工生命模拟程序。
[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl
翻译 - Thrust是一个类似于C ++标准库的C ++并行编程库。