1.jax-ml / jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Ranked by Attention Score: stars gained over the last 7 complete days
10 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Deep Learning for humans
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
Pretrained model hub for Keras 3.
Efficiently computes derivatives of NumPy code.
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments