Module optim 

Optimizers.

This module provides small, allocation-free-per-step optimizers that update an Mlp given a set of Gradients.

Design notes:

• Optimizer state (momentum/Adam moments) lives outside the model.
• The training loop owns the optimizer state and reuses it across steps.

Structs

Sgd

Stochastic gradient descent with a fixed learning rate.

Enums

Optimizer

Optimizer choice for training.

OptimizerState

Owned optimizer state.