Machine Learning

Another area of my interest. Neural nets, math under the hood. It's all here. Similar to the algorithms section, I strive for articles simplicity. As full-time ML engineer, I try to find something interesting and useful for you

Machine Learning

Understanding Flash Attention: Writing the Algorithm from Scratch in Triton

Why is Flash Attention so fast? Find out how Flash Attention works. Afterward, we'll polish our understanding by writing a GPU kernel of the algorithm in Triton.

6 days ago • 10 min read

Machine Learning

Speed Up PyTorch With Custom Kernels. But It Gets Progressively Darker

It's all about making your models run faster, from flicking a magic “compile” switch to writing your own custom GPU code. In each step, we’ll implement an innocent softmax function, but things are about to get dark by the end.

15 days ago • 7 min read

Machine Learning

Simple Ways to Speed Up Your PyTorch Model Training

If all machine learning engineers want one thing, it's faster model training — maybe after good test metrics.

8 months ago • 12 min read

Code

I Contributed to PyTorch. Here's What I Learned

When you see something that does not work in an omnipresent framework, you believe it can't be completely broken, right?

2 years ago • 3 min read

Machine Learning

How Deep Neural Networks Work

Here, I combine the explanation of Neural Nets with coding. By the end, we will develop a basic neural network and try to solve usual problems

5 years ago • 8 min read