Explore Projects
Discover 133 open source projects
Showing 21-40 of 133 projects
replicate/cog
A set of containers for running machine learning models and applications on various ML frameworks.
deepseek-ai/DeepEP
DeepEP is an efficient expert-parallel communication library for CUDA-based applications.
NVIDIA/cuda-samples
NVIDIA CUDA samples that demonstrate features of the CUDA Toolkit for GPU-accelerated development.
catboost/catboost
A high-performance gradient boosting library for machine learning tasks on CPUs and GPUs.
kroma-network/tachyon
A modular ZK backend accelerated by GPU for building blockchain and cryptocurrency applications.
InternLM/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving large language models (LLMs).
LMCache/LMCache
Supercharge your large language models (LLMs) with the fastest key-value cache layer for lightning-fast inference.
hybridgroup/gocv
A Go package for computer vision using OpenCV 4 and beyond, with support for DNN, CUDA, and more.
XuehaiPan/nvitop
An interactive NVIDIA-GPU process viewer and management tool for developers working with GPU-accelerated applications.
ethereum-mining/ethminer
An Ethereum miner with support for OpenCL, CUDA, and stratum that can be used for mining purposes.
chainer/chainer
A flexible, high-performance deep learning framework for Python that runs on GPUs.
chrxh/alien
ALIEN is a CUDA-powered artificial life simulation program for exploring open-ended evolution.
LWJGL/lwjgl3
A Java library that provides cross-platform access to native APIs for graphics, audio, parallel computing, and XR development.
rapidsai/cuml
A high-performance machine learning library for CUDA-enabled GPUs, accelerating data science workflows.
Rust-GPU/rust-cuda
Rust-CUDA is an ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
flashinfer-ai/flashinfer
A Python library for serving large language models (LLMs) with high performance, including GPU acceleration and distributed inference.
shader-slang/slang
A C++ library that makes it easier to work with shaders across different graphics APIs like CUDA, D3D12, GLSL, and Vulkan.
NVIDIA/thrust
A C++ parallel algorithms library that provides high-performance GPU acceleration for scientific computing and data analysis.
arrayfire/arrayfire
ArrayFire is a general-purpose GPU library that provides a high-performance, cross-platform programming interface for developers.
nerfstudio-project/gsplat
Highly performant CUDA-accelerated library for gaussian splatting, useful for AI and computer vision applications.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.