PyTorch

Implementing LLaMA 4 from Scratch

A line-by-line detailed explainer (with code).

May 17 •

Memory Pinning to Accelerate Model Training

A simple technique, and some key considerations.

May 7 •

Knowledge Distillation using Teacher Assistant

Improved model compression.

Apr 25 •

Implementing Knowledge Distillation From Scratch

...to compress ML models.

Mar 10 •

4 Strategies for Multi-GPU Training

...explained visually.

Feb 12 •

4 Ways to Test ML Models in Production

...explained visually.

Feb 3 •

From PyTorch to PyTorch Fabric

Scale model training with 4 small changes.

Nov 6, 2024 •

Implementing a Siamese Network

A beginner-friendly implementation guide.

Sep 29, 2024 •

Contrastive Learning Using Siamese Networks

Building a face unlock system.

Sep 28, 2024 •

Memory Pinning to Accelerate Model Training

A simple technique, and some key considerations.

Sep 13, 2024 •

A Counterintuitive Behaviour of PyTorch DataLoader

...which most PyTorch users aren't aware of.

Sep 6, 2024 •

A Crash Course on Graph Neural Networks — Part 3

Implementation included.

Sep 3, 2024 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts