Showing 17 of 17 projects
A Python package for tensor computation with GPU acceleration and dynamic neural networks built on a tape-based autograd system.
A Rust-based deep learning framework and tensor library optimized for flexibility, efficiency, and cross-platform portability.
A Python library for flexible and readable tensor operations across numpy, PyTorch, JAX, TensorFlow, and other frameworks.
Multi-dimensional arrays (tensors) and numerical definitions for Elixir, enabling machine learning and scientific computing.
Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
A deep learning library in Rust featuring shape-checked tensors and neural networks with compile-time safety.
A deep learning library for Rust featuring shape-checked tensors and neural networks with compile-time safety.
TensorLy: Tensor Learning in Python.
A tensor library for differentiable functional programming in F#, with PyTorch-like APIs and GPU support.
OCaml bindings for PyTorch, providing NumPy-like tensor computations with GPU acceleration and automatic differentiation.
A Swift library providing numpy-like multi-dimensional data structures and operations for numerical computing.
A core scientific computing library for Crystal providing n-dimensional tensors, linear algebra, GPU acceleration, and automatic differentiation.
A Swift library for accelerated tensor operations and dynamic neural networks with automatic differentiation, supporting all Apple platforms and Linux.
A learning-focused, high-performance tensor computation library built from scratch in Rust with automatic differentiation and CPU/CUDA backends.
Type-safe n-dimensional arrays (tensors) in Scala 3 with compile-time shape, axis label, and data type validation.
A Torch-like deep learning framework for JavaScript with direct tensor and autograd operations.
A JavaScript-native machine learning framework with PyTorch-aligned APIs, built from scratch on WebGPU for dynamic graph execution and model interpretability.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.