Transformations That Change Everything
Feb 9 · 10 min read · Last week, we learned that JAX makes code fast through JIT compilation. We took a matrix multiplication from 2 seconds to 0.001 seconds with a single decorator. But speed isn't JAX's only trick. The real power of JAX lies in its transformations; func...
Join discussion
Why JAX? The NumPy You Know, But Faster
Feb 2 · 9 min read · If you've been doing machine learning in Python for any length of time, you've written code like this: import numpy as np x = np.random.randn(1000, 1000) y = np.random.randn(1000, 1000) result = np.dot(x, y) NumPy is comfortable. It's the first thi...
Join discussion
My Hands-On Experience with Tunix: JAX Native Powers the Future of LLM Tuning with Tunix
Oct 3, 2025 · 15 min read · Introduction As someone who's spent countless hours wrestling with LLM post-training pipelines, I was excited to try out Tunix, Google's newly released JAX-native library specifically built for aligning language models. After spending the last few da...
Join discussionVision Transformers in JAX
Jun 21, 2025 · 15 min read · Transformers were introduced in 2017 and changed the course of Deep Learning research for many forthcoming years. Naturally, they were also adopted in the computer vision ecosystem which was till then, dominated by Convolutional Neural Networks or Co...
Join discussion
Getting Started with JAX: Modern Deep Learning Framework
Jun 4, 2025 · 13 min read · Machine Learning frameworks make our lives easier by offering built-in methods for faster prototyping and optimized GPU training. They also help by providing robust and scalable solutions which help engineers implement state-of-the-art models in a be...
Join discussion
Building Convolutional Neural Networks in JAX
Mar 12, 2025 · 9 min read · Introduction Deep learning has revolutionized the field of artificial intelligence, and at the heart of this revolution are Convolutional Neural Networks (CNNs). CNNs have become the go-to architectures for tasks involving images, such as object dete...
TVTheodore commented
Deep Learning Frameworks
Sep 9, 2024 · 4 min read · Hello! Welcome to another surprise mid-series special! 🤗 Some time back I contributed to a project called unify.ai. The vision of unify.ai is to create a platform that unites popular machine-learning frameworks and models through APIs. So I thought ...
Join discussion
JAX vs PyTorch: Ultimate Deep Learning Framework Comparison
Jul 17, 2024 · 10 min read · Introduction Deep learning has become a popular field in machine learning, and there are several frameworks available for building and training deep neural networks. Two of the most popular deep learning frameworks are JAX and PyTorch. JAX, built on ...
Join discussion