Don't import it. Build it.

Build your own ML framework — from tensors to systems.

Preview · Classroom ready Fall 2026

An educational framework for building and optimizing ML — understand how PyTorch, TensorFlow, and JAX really work.

TinyTorch is usable today for self-paced learning and active course pilots. APIs, instructor packaging, and classroom workflows will continue to stabilize through the Fall 2026 classroom release.

Start Building →

⭐ ... stars on GitHub — add yours and support free ML education

🔧 Build each piece — Tensors, autograd, attention. No magic imports.

📚 Recreate history — Perceptron → CNN → Transformers → MLPerf.

⚡ Understand systems — Memory, compute, optimization trade-offs.

🎯 Debug anything — OOM, NaN, slow training—because you built it.

Recreate ML History

Walk through ML history by rebuilding its greatest breakthroughs with YOUR TinyTorch implementations. Click each milestone to see what you’ll build and how it shaped modern AI.

1958

The Perceptron

The first trainable neural network

Input → Linear → Sigmoid → Output

1969

XOR Crisis

Minsky & Papert expose limits of single-layer networks

Input → Linear → Sigmoid → FAIL!

1986

MLP Revival

Backpropagation enables deep learning (95%+ MNIST)

Images → Flatten → Linear → ... → Classes

1998

CNN Revolution 🎯

Spatial intelligence unlocks computer vision (75%+ CIFAR-10)

Images → Conv → Pool → ... → Classes

2017

Transformer Era

Attention launches the LLM revolution

Tokens → Attention → FFN → Output

2018–Present

MLPerf Benchmarks

Production optimization (8-16× smaller, 12-40× faster)

Profile → Compress → Accelerate

Why Build Instead of Use?

"Building systems creates irreversible understanding."

Traditional ML Education

import torch
model = torch.nn.Linear(784, 10)
output = model(input)
# When this breaks, you're stuck

Problem: You can’t debug what you don’t understand.

TinyTorch: Build → Use → Reflect

# BUILD it yourself
class Linear:
    def forward(self, x):
        return x @ self.weight + self.bias

# USE it on real data
loss.backward()  # YOUR autograd