1.pytorch / pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
+6,186 stars
from 98,884 · score 8.73
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
88 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
2.bendlang / bend
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
+5,645 stars
from 18,979 · score 8.64
3.exelban / stats
macOS system monitor in your menu bar
+4,781 stars
from 38,247 · score 8.47
4.seerge / g-helper
Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and more.
+3,024 stars
from 12,820 · score 8.01
5.alacritty / alacritty
A cross-platform, OpenGL terminal emulator.
+2,759 stars
from 63,345 · score 7.92
6.Rem0o / FanControl.Releases
This is the release repository for Fan Control, a highly customizable fan controlling software for Windows.
+2,083 stars
from 19,198 · score 7.64
7.gfx-rs / wgpu
A cross-platform, safe, pure-Rust graphics API.
+1,533 stars
from 16,907 · score 7.34
8.cupy / cupy
NumPy & SciPy for GPU
+1,513 stars
from 10,877 · score 7.32
9.deepspeedai / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
+1,292 stars
from 41,989 · score 7.16
10.NVIDIA / cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
+1,085 stars
from 9,599 · score 6.99
11.skypilot-org / skypilot
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
+907 stars
from 9,870 · score 6.81
12.openwall / john
John the Ripper jumbo - advanced offline password cracker, which supports hundreds of hash and cipher types, and runs on many operating systems, CPUs, GPUs, and even some FPGAs
+877 stars
from 12,974 · score 6.78
13.isl-org / Open3D
Open3D: A Modern Library for 3D Data Processing
+673 stars
from 13,493 · score 6.51
14.apache / tvm
Open Machine Learning Compiler Framework
+623 stars
from 13,263 · score 6.44
15.harfbuzz / harfbuzz
HarfBuzz text shaping engine
+610 stars
from 5,580 · score 6.42
16.Syllo / nvtop
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
+570 stars
from 10,546 · score 6.35
17.PavelDoGreat / WebGL-Fluid-Simulation
Play with fluids in your browser (works even on mobile)
+556 stars
from 16,231 · score 6.32
18.NVIDIA / nccl
Optimized primitives for collective multi-GPU communication
+541 stars
from 4,659 · score 6.30
19.triton-inference-server / server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
+533 stars
from 10,589 · score 6.28
20.neovide / neovide
No Nonsense Neovim Client in Rust
+460 stars
from 14,833 · score 6.13
21.taichi-dev / taichi
Productive, portable, and performant GPU programming in Python.
+408 stars
from 28,032 · score 6.01
22.fastai / fastai
The fastai deep learning library
+393 stars
from 27,863 · score 5.98
23.catboost / catboost
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
+318 stars
from 8,868 · score 5.77
24.deepflowio / deepflow
eBPF Observability - Distributed Tracing and Profiling
+278 stars
from 4,034 · score 5.63
25.google / tf-quant-finance
High-performance TensorFlow library for quantitative finance.
+258 stars
from 5,298 · score 5.56
26.gpujs / gpu.js
GPU Accelerated JavaScript
+211 stars
from 15,308 · score 5.36
27.NVIDIA / cudf
cuDF - GPU DataFrame Library
+206 stars
from 9,581 · score 5.33
28.ChartGPU / ChartGPU
Beautiful, open source, WebGPU-based charting library
+205 stars
from 3,060 · score 5.33
29.plasma-umass / scalene
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
+197 stars
from 13,345 · score 5.29
30.gpuweb / gpuweb
Where the GPU for the Web work happens!
+181 stars
from 5,345 · score 5.20
31.defilantech / LLMKube
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
+178 stars
from 71 · score 5.19
32.gogpu / gogpu
Pure Go GPU Application Framework — windowing, input, lifecycle, platform abstraction. Part of the GoGPU ecosystem.
+164 stars
from 263 · score 5.11
33.ashvardanian / StringZilla
Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and memory ops 🦖
+159 stars
from 3,420 · score 5.08
34.NVIDIA / cuml
NVIDIA cuML: GPU-Accelerated Machine Learning
+153 stars
from 5,163 · score 5.04
35.Novum / vkQuake
Vulkan Quake port based on QuakeSpasm
+150 stars
from 2,163 · score 5.02
36.NVIDIA / nvidia-dockerArchived
Build and run Docker containers leveraging NVIDIA GPUs
+146 stars
from 17,461 · score 4.99
37.intel / ipex-llmArchived
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
+125 stars
from 8,720 · score 4.84
38.deeplearning4j / deeplearning4j
Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...
+110 stars
from 14,163 · score 4.71
39.graphistry / pygraphistry
PyGraphistry is a Python library to quickly load, shape, embed, and explore big graphs with the GPU-accelerated Graphistry visual graph analyzer
+107 stars
from 2,469 · score 4.68
40.webgpu-tools / wesl-spec
A portable and modular superset of WGSL
+103 stars
from 239 · score 4.64
41.gogpu / wgpu
Pure Go WebGPU Implementation
+103 stars
from 93 · score 4.64
42.h2oai / h2o-3
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
+98 stars
from 7,422 · score 4.60
43.rapidsai / cugraph
cuGraph - RAPIDS Graph Analytics Library
+91 stars
from 2,161 · score 4.52
44.unslothai / hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
+90 stars
from 2,439 · score 4.51
45.Gamua / Starling-Framework
The Cross Platform Game Engine
+87 stars
from 3,033 · score 4.48
46.MFlowCode / MFC
Exascale multiphase flow solver — 2025 Gordon Bell Prize Finalist | 200T grid points on 43K+ GPUs
+86 stars
from 352 · score 4.47
47.Sergio0694 / ComputeSharp
A .NET library to run C# code in parallel on the GPU through DX12, D2D1, and dynamically generated HLSL compute and pixel shaders, with the goal of making GPU computing easy to use for all .NET developers! 🚀
+83 stars
from 3,105 · score 4.43
48.koide3 / fast_gicp
A collection of GICP-based fast point cloud registration algorithms
+78 stars
from 1,626 · score 4.37
49.FluidGroup / Brightroom
📷 A composable image editor using Core Image and Metal.
+73 stars
from 3,614 · score 4.30
50.gogpu / gg
Enterprise-grade 2D graphics library for Go. Pure Go, zero CGO. Part of GoGPU ecosystem.
+70 stars
from 98 · score 4.26
51.m4rs-mt / ILGPU
ILGPU JIT Compiler for high-performance .Net GPU programs
+66 stars
from 1,697 · score 4.20
52.runmat-org / runmat
Open source math and physics engine that executes MATLAB-syntax code. Features a modern compiler, automatic GPU acceleration for large calculations, and support for math on geometry / FEA calculations.
+66 stars
from 205 · score 4.20
53.go-webgpu / goffi
Pure Go FFI for WebGPU - CGO-free GPU access via wgpu-native bindings
+63 stars
from 39 · score 4.16
54.EQMG / Acid
A high speed C++17 Vulkan game engine
+61 stars
from 1,969 · score 4.13
55.MetalPetal / MetalPetal
A GPU accelerated image and video processing framework built on Metal.
+58 stars
from 2,139 · score 4.08
56.elixir-nx / nx
Multi-dimensional arrays (tensors) and numerical definitions for Elixir
+50 stars
from 2,869 · score 3.93
57.datoviz / datoviz
⚡ Datoviz: high-performance GPU rendering for scientific data visualization
+48 stars
from 777 · score 3.89
58.arrayfire / arrayfire
ArrayFire: a general purpose GPU library.
+41 stars
from 4,867 · score 3.74
59.jerryji1993 / DNABERT
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
+41 stars
from 742 · score 3.74
60.NVIDIA / MatX
An efficient C++20 GPU numerical computing library with Python-like syntax
+40 stars
from 1,412 · score 3.71
61.Devsh-Graphics-Programming / Nabla
Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android
+40 stars
from 681 · score 3.71
62.Celtoys / Remotery
Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer
+38 stars
from 3,281 · score 3.66
63.kondrak / vkQuake2
id Software's Quake 2 v3.21 with mission packs and Vulkan support (Windows, Linux, macOS, FreeBSD, Raspberry Pi 4)
+33 stars
from 989 · score 3.53
64.parca-dev / parca-agent
eBPF based always-on CPU/GPU profiler auto-discovering targets in Kubernetes and systemd, zero code changes or restarts needed!
+33 stars
from 716 · score 3.53
65.e-ago / bitcracker
BitCracker is the first open source password cracking tool for memory units encrypted with BitLocker
+27 stars
from 949 · score 3.33
66.neka-nat / cupoch
Robotics with GPU computing
+26 stars
from 1,039 · score 3.30
67.gogpu / naga
Pure Go Shader Compiler — WGSL to SPIR-V, MSL, GLSL, HLSL, DXIL. Zero CGO.
+24 stars
from 32 · score 3.22
68.eyalroz / cuda-api-wrappers
Thin, unified, C++-flavored wrappers for the CUDA APIs
+23 stars
from 883 · score 3.18
69.gfx-rs / gfx
[maintenance mode] A low-overhead Vulkan-like GPU API for Rust.
+22 stars
from 5,373 · score 3.14
70.ml-tooling / ml-workspace
🛠 All-in-one web-based IDE specialized for machine learning and data science.
+21 stars
from 3,528 · score 3.09
71.boostorg / compute
A C++ GPU Computing Library for OpenCL
+21 stars
from 1,645 · score 3.09
72.CEED / libCEED
CEED Library: Code for Efficient Extensible Discretizations
+19 stars
from 254 · score 3.00
73.vaneenige / phenomenon
⚡️ A fast 2kB low-level WebGL API.
+18 stars
from 1,831 · score 2.94
74.stotko / stdgpu
stdgpu: Efficient STL-like Data Structures on the GPU
+17 stars
from 1,257 · score 2.89
75.jpbruyere / vkvg
Vulkan 2D graphics library
+17 stars
from 806 · score 2.89
76.NVIDIA / thrustArchived
[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl
+16 stars
from 4,978 · score 2.83
77.openfl / starling
Known as the "Cross-Platform Game Engine", Starling is a popular Stage3D framework for OpenFL and Haxe
+11 stars
from 258 · score 2.48
78.Xtra-Computing / thundersvm
ThunderSVM: A Fast SVM Library on GPUs and CPUs
+9 stars
from 1,618 · score 2.30
79.uncomplicate / neanderthal
Fast Clojure Matrix Library
+9 stars
from 1,123 · score 2.30
80.NVIDIA / DIGITSArchived
Deep Learning GPU Training System
+8 stars
from 4,166 · score 2.20
81.google / gapid
Graphics API Debugger
+6 stars
from 2,233 · score 1.95
82.Xtra-Computing / thundergbm
ThunderGBM: Fast GBDTs and Random Forests on GPUs
+6 stars
from 710 · score 1.95
83.DiffSharp / DiffSharp
DiffSharp: Differentiable Functional Programming
+4 stars
from 612 · score 1.61
84.LaurentMazare / ocaml-torch
OCaml bindings for PyTorch
+4 stars
from 440 · score 1.61
85.load1n9 / caviar
⚡ Blazing fast, modern, Game Engine powered by WebGPU for Deno and the browser
+4 stars
from 168 · score 1.61
86.libmir / dcompute
DCompute: Native execution of D on GPUs and other Accelerators
+4 stars
from 140 · score 1.61
87.NVIDIA / libcudacxxArchived
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
+3 stars
from 2,297 · score 1.39
88.uncomplicate / bayadera
High-performance Bayesian Data Analysis on the GPU in Clojure
+2 stars
from 370 · score 1.10