#neural-networks

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Relax! Flux is the ML library that doesn't make you tensor

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Evaluation and Tracking for LLM Experiments and AI Agents

Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

Brevitas: neural network quantization in PyTorch

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Born is a modern ML framework for Go — train and deploy models as single binaries. Pure Go, zero CGO, GPU accelerated.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Message Passing Neural Networks for Molecule Property Prediction

JAX-based neural network library

[DEPRECATED] Moved to ROCm/rocm-libraries repo

💫 Industrial-strength Natural Language Processing (NLP) in Python

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/