TinyTorch

mirror of https://github.com/MLSysBook/TinyTorch.git synced 2026-03-12 07:53:34 -05:00

Files

Vijay Janapa Reddi 1fc1567e50 Stage 2: Add Module base class for clean layer definitions

- Add Module base class with automatic parameter registration
- Auto-registers Tensors with requires_grad=True as parameters
- Provides clean __call__ interface: model(x) instead of model.forward(x)
- Recursive parameter collection from sub-modules
- Update Dense to inherit from Module and use Parameter()
- Remove redundant __call__ method from Dense (provided by Module)
- Enables PyTorch-like syntax: optimizer = Adam(model.parameters())

2025-09-23 07:59:29 -04:00

01_setup

Update generated notebooks and package exports

2025-09-18 16:42:57 -04:00

02_tensor

Stage 1: Unify Tensor with requires_grad support for cleaner API

2025-09-23 07:56:46 -04:00

03_activations

Implement autograd support in activation functions (Module 03)

2025-09-21 10:28:21 -04:00

04_layers

Stage 2: Add Module base class for clean layer definitions