Open weights LLM from Google DeepMind.

A machine learning compiler for GPUs, CPUs, and ML accelerators

JAX-Toolbox

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in bot…

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

XLB: Accelerated Lattice Boltzmann (XLB) based on JAX for Physics-based ML

Icarogw is a pure python package to estimate population properties of noisy observations in presence of selection biases. The code is mostly used for gravitational waves observations.

An Open Source Machine Learning Framework for Everyone

Flax is a neural network library for JAX that is designed for flexibility.

Deep Learning Examples

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic …

Library to manipulate tensors on the GPU.

OS-agnostic, system-level binary package manager and ecosystem

The Python programming language

Deep Learning Tutorial notes and code. See the wiki for more info.

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning with Theano

A Machine Learning library based on Theano (fork by Olivier Delalleau)

Website and ideas page for Python's Google Summer of Code efforts

Numpy main repository