tinygrad is a compact end-to-end deep learning stack designed to sit somewhere between PyTorch and micrograd. It combines a tensor library, automatic differentiation, compiler, JIT execution, and neural network facilities in a deliberately small and hackable codebase.
Its execution engine supports a wide range of hardware backends while exposing much of the compiler and intermediate representation to developers.
This is free and open source software.
Key Features
- Tensor library with automatic differentiation.
- Intermediate representation and compiler for lowering computational kernels.
- Lazy execution enables operations to be fused into efficient kernels.
- JIT compilation and graph execution.
- Includes neural network layers and optimisers.
- Supports familiar PyTorch-style training loops.
- Provides datasets and other components needed for model training.
- Runs on CPUs and numerous hardware accelerators.
- Supports CUDA, AMD, Metal, OpenCL, Qualcomm, and WebGPU backends.
- Compiler and intermediate representation are designed to remain readable and hackable.
- Small codebase intended to minimise complexity.
Website: https://github.com/tinygrad/tinygrad
Support:
Developer: tiny corp
License: MIT License
tinygrad is written in Python and C. Learn Python with our recommended free books and free tutorials. Learn C with our recommended free books and free tutorials.
Related Software
| Deep Learning with Python | |
|---|---|
| TensorFlow | A very popular Deep Learning framework |
| PyTorch | Tensors and Dynamic neural networks in Python |
| Keras | High-level neural networks API |
| fastai | Simplifies training fast and accurate neural networks |
| tinygrad | Compact, lightweight deep learning framework |
| PyTorch Lightning | Framework for scaling PyTorch training workflows |
| JAX | High-performance numerical computing and ML library |
| PyTensor | Library for fast numerical computation |
| MindSpore | Framework for training and deploying neural networks |
| Elephas | Distributed deep learning with Keras and Spark |
| Chainer | Powerful, flexible, and intuitive framework for neural networks |
| Equinox | Neural network library for building flexible models with JAX |
| Caffe | Convolutional Architecture for Fast Feature Embedding |
| TFlearn | Deep learning library featuring a higher-level API for TensorFlow |
| MXNet | Flexible and efficient library |
| CNTK | Distributed deep learning |
| Neupy | Python library for neural networks and deep learning |
Read our verdict in the software roundup.
 Explore our carefully curated directory of recommended free and open source software, covering every major software category.The directory forms part of our extensive collection of articles for Linux enthusiasts. It includes hundreds of detailed reviews, together with free and open source alternatives to proprietary software from companies such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. LinuxLinks also covers interesting projects worth exploring, Linux-compatible hardware, free programming books and tutorials, and much more. Know a useful free and open source Linux application that we haven’t covered? Tell us about it using our submission form. |
Please read our Comment Policy before commenting.