Download
Hasktorch is a powerful Haskell library for tensor computation and neural network modeling, built on top of libtorch (the backend of PyTorch). It brings differentiable programming, automatic differentiation, and efficient tensor operations into Haskell’s strongly typed functional paradigm. This project is in active development, so expect changes to the library API as it evolves. We would like to invite new users to join our Hasktorch discord space for questions and discussions. Contributions/PR are encouraged. Hasktorch is a library for tensors and neural networks in Haskell. It is an independent open source community project which leverages the core C++ libraries shared by PyTorch.
Features
- High-performance tensor operations utilizing libtorch for CPU and GPU computation
- Support for both typed and untyped tensors to ensure type safety and flexibility
- Automatic differentiation for gradient-based optimization and learning
- Abundant mathematical operations including linear algebra, neural network layers, and probability distributions
- Lightweight, idiomatic Haskell design leveraging algebraic data types and functional composition
- Active open-source community with tutorials, examples, and multi-platform support (Linux, macOS, Nix, Docker)
Project Samples
Categories
LibrariesFollow Hasktorch
Other Useful Business Software
Build Securely on AWS with Proven Frameworks
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Hasktorch!
