Tensors and Dynamic neural networks in Python with strong GPU acceleration
- neural-network
- autograd
- gpu
- numpy
57,138 visible repositories in the index
1–24 of 842 · Most stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Google Research
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
The fundamental package for scientific computing with Python.
:partly_sunny: The right way to check the weather
Simulation platform for general-purpose robotics & embodied AI learning.
MLX: An array framework for Apple silicon
Optimizing compiler for React
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Play with fluids in your browser (works even on mobile)
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
SciPy library main repository
An extensive math library for JavaScript and Node.js
A computer algebra system written in pure Python
Count your code, quickly.
Open source code for AlphaFold 2.
Google's Operations Research tools:
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...
Open3D: A Modern Library for 3D Data Processing
NumPy & SciPy for GPU
A feature-rich weather app with good visualizations and more than 50 sources.
OpenGL Mathematics (GLM)
CUDA Templates and Python DSLs for High-Performance Linear Algebra
A modular geospatial engine written in JavaScript and TypeScript