A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
A re-implementation of Karpathy's micrograd in C
Efficiently computes derivatives of NumPy code.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
Automatic Sparse Differentiation in JAX.
Drop-in autodiff for NumPy.
Hardware accelerated, batchable and differentiable optimizers in JAX.
You like pytorch? You like micrograd? You love tinygrad! ❤️
