Vijay Janapa Reddi 6f0c96c130 Fix gradient flow with PyTorch-style requires_grad tracking ...

- Updated Linear layer to use autograd operations (matmul, add) for proper gradient propagation
- Fixed Parameter class to wrap Variables with requires_grad=True
- Implemented proper MSELoss and CrossEntropyLoss with backward chaining
- Added broadcasting support in autograd operations for bias gradients
- Fixed memoryview errors in gradient data extraction
- All integration tests now pass - neural networks can learn via backpropagation

2025-09-29 10:46:58 -04:00

..

backends

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

configs

Adds initial TinyTorch CLI and core structure

2025-07-09 00:23:19 -04:00

core

Fix gradient flow with PyTorch-style requires_grad tracking

2025-09-29 10:46:58 -04:00

datasets

Adds initial TinyTorch CLI and core structure

2025-07-09 00:23:19 -04:00

experimental

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

nn

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

optim

Organize package with nn and optim modules

2025-09-23 08:10:47 -04:00

profiler

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

quantization

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

utils

FOUNDATION: Establish AI Engineering as a discipline through TinyTorch

2025-09-25 11:16:28 -04:00

__init__.py

Organize package with nn and optim modules

2025-09-23 08:10:47 -04:00

_modidx.py

Fix module issues and create minimal MNIST training examples

2025-09-29 10:20:33 -04:00

tinygpt.py

Complete comprehensive system validation and cleanup

2025-09-23 10:00:33 -04:00