Open-source gpu-computing software
544 open-source libraries, tools and applications tagged gpu-computing, ranked by how closely gpu-computing is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
544 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| apache/singa Apache SINGA is a distributed deep learning platform for training neural networks across multiple devices and machines. It provides a C++ c… | 64 | 3606 | maintenance |
| scrya-com/rotorquant RotorQuant is a KV cache compression method for LLM inference that replaces full d×d orthogonal rotations with block-diagonal Clifford roto… | 47 | 1049 | active |
| brichard19/BitCrack BitCrack is a C++ command-line tool for brute-forcing Bitcoin private keys using CUDA (NVIDIA) or OpenCL (AMD/Intel) GPU acceleration. It w… | 23 | 1048 | active |
| NVIDIA/cuda-tile CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for optimizing CUDA kernels with tile-based computati… | 80 | 1035 | active |
| alex-petrenko/sample-factory Sample Factory is a high-throughput Python reinforcement learning library implementing synchronous and asynchronous policy gradient algorit… | 66 | 1026 | active |
| Accelerate Accelerate is an embedded domain-specific language in Haskell for high-performance, multi-dimensional array computations. Programs written … | 59 | 1020 | active |
| facebookresearch/PyTorch-BigGraph PyTorch-BigGraph is a distributed system for learning embeddings of very large graph-structured data, scaling to billions of entities and t… | 10 | 3454 | maintenance |
| NVIDIA/cudf-spark A plugin library for Apache Spark from NVIDIA that leverages GPUs via the cuDF (CUDA DataFrame) library to accelerate Spark SQL and DataFra… | 97 | 1012 | active |
| facebookresearch/fairscale FairScale is a PyTorch extension library providing composable modules and APIs for high-performance, large-scale distributed training, incl… | 27 | 3403 | maintenance |
| tomgoldstein/loss-landscape PyTorch code for visualizing the loss landscape of neural networks, from the NIPS 2018 paper 'Visualizing the Loss Landscape of Neural Nets… | 32 | 3205 | maintenance |
| NebuTech/NBMiner NBMiner is a closed-source GPU cryptocurrency miner supporting algorithms like ethash, etchash, kawpow, cuckoo_ae, beamv3, octopus, and erg… | 23 | 3177 | maintenance |
| turbo/js turbo.js is a small JavaScript library for GPGPU computing in the browser, letting you run parallel kernels written in GLSL over large Floa… | 10 | 2655 | maintenance |
| trexminer/T-Rex T-Rex is a closed-source NVIDIA GPU cryptocurrency miner supporting algorithms like Ethash, Etchash, Autolykos2, Kawpow, and Octopus, with … | 23 | 2640 | maintenance |
| microsoft/DirectML DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning that provides GPU acceleration across DirectX … | 55 | 2582 | maintenance |
| astooke/rlpyt A PyTorch library providing modular, high-throughput implementations of deep reinforcement learning algorithms, covering policy gradient, d… | 32 | 2276 | maintenance |
| QuipNetwork/quip-miner A Python mining stack for the Quip Network Substrate chain that coordinates CPU (simulated annealing), GPU (CUDA/Metal/Modal), and QPU (D-W… | 61 | 11592 | experimental |
| S-LoRA/S-LoRA S-LoRA is a serving system for large language models that scales to thousands of concurrent LoRA adapters on one or more GPUs. It uses Unif… | 10 | 1926 | maintenance |
| KytyPS5/KytyPS5 KytyPS5 is a free, open-source PlayStation 5 emulator written in C++, based on a heavily modified version of Kyty. It can boot a limited se… | 78 | 9260 | experimental |
| tunabrain/tungsten Tungsten is a high-performance physically based renderer written in C++11 that simulates full light transport through arbitrary geometry us… | 23 | 1834 | maintenance |
| fholger/openvr_fsr A modified OpenVR DLL that injects AMD FidelityFX Super Resolution or NVIDIA Image Scaling upscaling into D3D11-based SteamVR games to boos… | 23 | 1812 | maintenance |
| kmkolasinski/AwesomeBump AwesomeBump is a free open-source desktop application built with Qt that generates normal, height, specular, ambient occlusion, metallic, a… | 23 | 1782 | maintenance |
| facebookresearch/TensorComprehensions Tensor Comprehensions is a C++ library with a Python API that provides a domain-specific language for expressing machine learning workloads… | 10 | 1769 | maintenance |
| GPGPU-Sim GPGPU-Sim is a cycle-level simulator that models contemporary NVIDIA GPUs running CUDA and OpenCL workloads, including support for TensorCo… | 78 | 1750 | maintenance |
| boostorg/compute Boost.Compute is a C++ GPU/parallel-computing library built on OpenCL, providing a thin C++ wrapper over the OpenCL API plus an STL-like in… | 72 | 1663 | maintenance |
| calebwin/emu Emu is a Rust GPGPU library providing a CUDA-like compute-focused abstraction over WebGPU. It offers type-safe GPU data boxing, an auto-man… | 32 | 1606 | maintenance |
| gpushare A Kubernetes scheduler extender that enables multiple pods to share the same NVIDIA GPU device, increasing GPU utilization for inference an… | 32 | 1532 | maintenance |
| pytorch/gloo Gloo is a C++ collective communications library providing primitives like barrier, broadcast, and allreduce for multi-machine machine learn… | 75 | 1456 | maintenance |
| VictorTaelin/WebMonkeys A JavaScript library that lets you spawn thousands of parallel tasks on the GPU through a minimal set/get/work API, using GLSL 1.0 without … | 32 | 1443 | maintenance |
| Knet Knet (Koç University deep learning framework) is a deep learning library implemented in Julia with GPU support and automatic differentiatio… | 23 | 1431 | maintenance |
| VerticalResearchGroup/miaow MIAOW is an open source GPU implementation of the AMD Southern Islands ISA written in Verilog. It was developed as a research project at th… | 36 | 1420 | maintenance |
| NVIDIA/VideoProcessingFramework NVIDIA's Video Processing Framework (VPF) provides C++ libraries with Python bindings for fully hardware-accelerated video decoding, encodi… | 10 | 1379 | maintenance |
| chengzeyi/stable-fast Stable Fast is an ultra lightweight performance optimization framework for HuggingFace Diffusers pipelines on NVIDIA GPUs. It achieves SOTA… | 21 | 1305 | maintenance |
| DeepGraphLearning/graphvite GraphVite is a general, high-performance graph embedding engine written in C++ with Python bindings, supporting node embedding, knowledge g… | 32 | 1270 | maintenance |
| Yours3lf/rpi-vk-driver A low-level GPU driver for the Broadcom Videocore IV GPU found in Raspberry Pi boards, implementing a subset of the Vulkan API. It is not o… | 23 | 1241 | maintenance |
| anderskm/gputil GPUtil is a Python module that queries NVIDIA GPU status (memory usage, load, availability) by wrapping the nvidia-smi command-line tool. I… | 61 | 1215 | maintenance |
| ROCm/MIOpen MIOpen is AMD's open-source library providing high-performance GPU kernels for machine learning primitives (convolutions, normalization, ac… | 89 | 1195 | maintenance |
| Rust-GPU/rust-cuda An ecosystem of Rust libraries and tools for writing and executing fast GPU code fully in Rust, targeting NVIDIA CUDA. It lets developers a… | 66 | 5399 | experimental |
| punica-ai/punica Punica is a Python system for serving many LoRA-finetuned LLMs from a single copy of the base model on one GPU, using a custom CUDA kernel … | 10 | 1175 | maintenance |
| JPaulMora/Pyrit Pyrit is a WPA/WPA2-PSK precomputed cracker that builds massive databases of pre-computed Pairwise Master Keys using multi-core CPUs and GP… | 64 | 1140 | maintenance |
| fff-rs/juice Juice is a Rust machine learning framework ('The Hacker's Machine Learning Engine') built on the Coaster hardware abstraction layer, suppor… | 32 | 1132 | maintenance |
| microsoft/Windows-Machine-Learning Microsoft's Windows Machine Learning samples and tools repository, providing a high-performance ONNX inference API powered by ONNX Runtime … | 35 | 1122 | maintenance |
| baidu-research/DeepBench DeepBench is a benchmarking suite from Baidu Research that measures the performance of fundamental deep learning operations (matrix multipl… | 32 | 1109 | maintenance |
| openai/blocksparse A Python package of TensorFlow ops and custom CUDA GPU kernels for block-sparse matrix multiplication and convolution, plus related ops lik… | 10 | 1067 | maintenance |
| NVlabs/cuda-oxide cuda-oxide is an experimental rustc codegen backend that compiles Rust GPU kernels directly to CUDA PTX, letting you write SIMT device code… | 82 | 3746 | experimental |
| jephersonRD/Maquina-V5 A collection of Google Colab notebooks and scripts that spin up a temporary cloud gaming PC with an NVIDIA Tesla T4 GPU, install Steam, and… | 47 | 2336 | experimental |
| chelsea0x3b/dfdx A Rust deep learning library providing shape-checked tensors and neural network building blocks with compile-time verification of tensor op… | 23 | 1934 | experimental |
| nestrilabs/nestri Nestri is an open-source cloud gaming platform that runs games and apps inside hardware-accelerated micro-VMs and streams them to clients o… | 91 | 1752 | experimental |
| AnswerDotAI/fsdp_qlora A training script/library from Answer.AI that combines QLoRA (quantized LoRA) with PyTorch FSDP to fine-tune large language models like Lla… | 27 | 1554 | experimental |
| fastplotlib/fastplotlib fastplotlib is a GPU-accelerated scientific plotting library for Python built on the pygfx rendering engine, which uses WGPU (Vulkan, DX12,… | 94 | 1532 | experimental |
| hughperkins/VeriGPU VeriGPU is an open-source GPU written in SystemVerilog, loosely based on the RISC-V ISA and targeting eventual ASIC tape-out for machine le… | 32 | 1395 | experimental |
| tspeterkim/flash-attention-minimal A minimal ~100-line CUDA re-implementation of the Flash Attention forward pass, loadable as a PyTorch extension. It is designed as an educa… | 26 | 1192 | experimental |
| thinking-machines-lab/batch_invariant_ops A Python library that replaces standard PyTorch CUDA kernels with batch-invariant versions, ensuring identical results regardless of batch … | 37 | 1080 | experimental |
| apache/mxnet Apache MXNet is a deep learning framework offering a hybrid front-end that mixes imperative (Gluon) and symbolic programming, with a dynami… | 10 | 20804 | abandoned |
| microsoft/CNTK The Microsoft Cognitive Toolkit (CNTK) is an open-source deep-learning toolkit that describes neural networks as directed computational gra… | 10 | 17590 | abandoned |
| intel/ipex-llm IPEX-LLM is a PyTorch LLM acceleration library for Intel hardware (iGPU, NPU, Arc/Flex/Max GPUs, and CPU), offering low-bit quantization (F… | 10 | 8845 | abandoned |
| TensorFlow.js tfjs-core was the core WebGL-accelerated tensor computation library behind TensorFlow.js, providing linear algebra operations and automatic… | 10 | 8425 | abandoned |
| tiny-dnn/tiny-dnn tiny-dnn is a header-only, dependency-free deep learning framework written in C++14, designed for training and running neural networks on r… | 23 | 6028 | abandoned |
| Leaf Leaf is an open-source machine learning framework written in Rust for building classical, deep, or hybrid ML applications, inspired by Tens… | 32 | 5540 | abandoned |
| google/tf-quant-finance A high-performance TensorFlow library for quantitative finance providing foundational numerical methods, ODE/PDE solvers, and pricing model… | 62 | 5526 | abandoned |
| amazon-archives/amazon-dsstne DSSTNE (Deep Scalable Sparse Tensor Network Engine) is a C++ GPU library from Amazon for training and deploying deep learning recommendatio… | 10 | 4390 | abandoned |
| NVIDIA/DIGITS DIGITS is a web application for training deep learning models on GPUs, supporting frameworks like Caffe, Torch, and TensorFlow with a brows… | 10 | 4176 | abandoned |
| NervanaSystems/neon neon was Intel Nervana's reference deep learning framework in Python, focused on best-in-class training performance on CPUs, GPUs, and Nerv… | 10 | 3860 | abandoned |
| fo40225/tensorflow-windows-wheel A repository of prebuilt TensorFlow wheel binaries for 64-bit Windows, including CPU-only and CUDA/cuDNN GPU builds with AVX2 and SSE2 (non… | 32 | 3665 | abandoned |
| apple/tensorflow_macos A pre-release fork of TensorFlow and TensorFlow Addons for macOS 11.0+ that provides hardware acceleration on Apple Silicon and Intel Macs … | 10 | 3643 | abandoned |
| haxiomic/GPU-Fluid-Experiments A cross-platform GPU-accelerated fluid simulation experiment written in Haxe, with a browser-based interactive demo. It renders real-time f… | 32 | 3064 | abandoned |
| facebookarchive/fb.resnet.torch A Torch (Lua) implementation of ResNet residual networks for image classification, with training scripts for ImageNet and pretrained models… | 10 | 2361 | abandoned |
| AutoAWQ AutoAWQ is a Python library implementing the Activation-aware Weight Quantization (AWQ) algorithm for 4-bit quantization of large language … | 10 | 2346 | abandoned |
| openai/sparse_attention A Python library of sparse attention primitives from OpenAI's Sparse Transformers paper, including fused normal attention and strided/fixed… | 10 | 1612 | abandoned |
| ELS-RD/kernl Kernl is an open-source PyTorch model optimization library that accelerates transformer inference on GPUs with a single line of code, using… | 10 | 1583 | abandoned |
| andersbll/deeppy DeepPy is a Pythonic deep learning framework built on top of NumPy, with optional CUDA acceleration via the cudarray library. It provides a… | 32 | 1371 | abandoned |
| happynear/caffe-windows A Windows-specific fork of the Caffe deep learning framework with preconfigured Visual Studio project files, enabling users to build Caffe … | 23 | 1310 | abandoned |
| pluskid/Mocha.jl Mocha.jl is a deep learning framework for Julia, inspired by Caffe, providing modular layers, solvers, and support for training convolution… | 32 | 1284 | abandoned |
| lachesis/scallion Scallion is a GPU-accelerated (OpenCL) vanity key generator that creates custom .onion addresses for Tor hidden services and vanity GPG key… | 23 | 1276 | abandoned |
| rosejn/cortex Cortex is a Clojure machine learning library providing neural networks, regression, and feature learning on the JVM, with optional GPU acce… | 32 | 1272 | abandoned |
| ivan-vasilev/neuralnetworks A Java library implementing deep learning algorithms and deep neural network architectures (MLPs, CNNs, RBMs, autoencoders, DBNs) with GPU … | 23 | 1236 | abandoned |
| eholk/harlan Harlan is a small domain-specific language implemented in Scheme for programming GPUs, compiled to OpenCL. It serves primarily as a researc… | 32 | 1191 | abandoned |
| hannes-brt/hebel Hebel is a GPU-accelerated deep learning library in Python built on PyCUDA, implementing feed-forward neural networks for classification an… | 23 | 1169 | abandoned |
| NVIDIA/tensorflow NVIDIA's fork of TensorFlow 1.15 providing GPU support for newer NVIDIA hardware and CUDA libraries after Google stopped maintaining the TF… | 10 | 1147 | abandoned |
| nanopool/Claymore-Dual-Miner Claymore's Dual GPU miner for AMD and NVIDIA cards, primarily mining Ethereum with a second coin like Decred, Siacoin, or Lbry in dual mode… | 10 | 1109 | abandoned |
| dmlc/minpy MinPy is a Python library providing a pure NumPy interface backed by MXNet, automatically dispatching operators to GPU when available and f… | 10 | 1094 | abandoned |
| NervanaSystems/maxas MaxAs is an assembler for NVIDIA Maxwell GPU architecture that assembles SASS (Shader Assembly) instructions, written in Perl. It enables l… | 10 | 1074 | abandoned |
| facebookarchive/fbcunn Facebook AI Research's CUDA-accelerated deep learning extension modules for the Torch-7 framework, including fast FFT-based convolutions, m… | 10 | 1058 | abandoned |
| ray-project/ray Ray is a unified open-source framework for scaling AI and Python applications, consisting of a core distributed runtime (tasks, actors, obj… | 99 | 44057 | stable |
| facebookresearch/faiss Faiss is a C++ library (with Python wrappers) for efficient similarity search and clustering of dense vectors, supporting indexes that scal… | 94 | 41147 | stable |
| BitNet bitnet.cpp is Microsoft's official inference framework for 1-bit large language models (BitNet b1.58), providing optimized CPU kernels with… | 62 | 40295 | active |
| huggingface/diffusers Hugging Face Diffusers is a Python library providing state-of-the-art pretrained diffusion models for generating images, videos, and audio … | 95 | 34736 | stable |
| tinygrad/tinygrad tinygrad is a small, hackable deep learning framework providing a PyTorch-like tensor library with autograd, plus a visible IR and compiler… | 88 | 33740 | active |
| Lightning-AI/pytorch-lightning PyTorch Lightning is a deep learning framework that organizes PyTorch code to eliminate boilerplate for training, finetuning, and scaling A… | 93 | 31417 | stable |
| karpathy/llm.c llm.c is a pure C/CUDA implementation for training large language models like GPT-2 and GPT-3, with no dependency on PyTorch or Python. It … | 34 | 31176 | active |
| MLX MLX is an array computation framework for machine learning on Apple silicon, developed by Apple ML research. It offers NumPy-like Python AP… | 95 | 28839 | active |
| Stability-AI/generative-models Stability AI's official repository of generative diffusion models, including Stable Diffusion, Stable Video, and SV4D 2.0 for image, video,… | 42 | 27300 | active |
| Apollo Apollo is an open-source autonomous driving platform providing a high-performance, modular software stack for developing, testing, and depl… | 54 | 26853 | active |
| PaddlePaddle PaddlePaddle is an industrial-grade deep learning framework written in C++ with Python APIs, supporting high-performance single-machine and… | 92 | 24105 | active |
| Tencent/ncnn ncnn is a high-performance neural network inference framework written in C++ and optimized for mobile, embedded, and desktop deployment. It… | 83 | 23907 | stable |
| Video2X Video2X is a machine learning-based video super-resolution and frame interpolation framework written in C/C++. It upscales videos and image… | 62 | 22307 | active |
| ONNX Runtime ONNX Runtime is a cross-platform, high-performance machine-learning accelerator for running inference and training on ONNX models. It suppo… | 100 | 22115 | stable |
| huggingface/candle Candle is a minimalist machine learning framework for Rust focused on performance and ease of use, with CPU and CUDA GPU support. It ships … | 74 | 21182 | active |
| NVIDIA/Megatron-LM NVIDIA's GPU-optimized library for training large transformer models at scale, comprising Megatron-LM (reference training scripts) and Mega… | 100 | 18178 | active |
| MNN MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba, supporting LLMs, vision, audio, and multimodal … | 90 | 16188 | active |
| tracel-ai/burn Burn is a Rust-based tensor library and deep learning framework supporting training and inference through a unified API. It JIT-compiles te… | 86 | 16008 | active |