Blog

Learning Triton One Kernel at a Time: Softmax featured image

Autonomous Driving

Learning Triton One Kernel at a Time: Softmax

Published on Towards Data Science

Ryan Pégoud

• Feb 19, 2026 • 1 min read

Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels featured image

Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels

Published on Towards Data Science

Ryan Pégoud

• Jan 16, 2026 • 1 min read

Learning Triton One Kernel at a Time: Softmax featured image

Learning Triton One Kernel at a Time: Softmax

Published on Towards Data Science

Ryan Pégoud

• Nov 23, 2025 • 1 min read

Learning Triton One Kernel At a Time: Matrix Multiplication featured image

Learning Triton One Kernel At a Time: Matrix Multiplication

Published on Towards Data Science

Ryan Pégoud

• Oct 15, 2025 • 1 min read

Learning Triton One Kernel At a Time: Vector Addition featured image

Learning Triton One Kernel At a Time: Vector Addition

Published on Towards Data Science

Ryan Pégoud

• Sep 27, 2025 • 1 min read

Rainbow: The Colorful Evolution of Deep Q-Networks 🌈 featured image

Reinforcement Learning

Rainbow: The Colorful Evolution of Deep Q-Networks 🌈

Published on Towards Data Science

Ryan Pégoud

• Jul 12, 2024 • 1 min read

A Practical Guide to Proximal Policy Optimization in JAX 📈 featured image

Reinforcement Learning

A Practical Guide to Proximal Policy Optimization in JAX 📈

Published on Towards Data Science

Ryan Pégoud

• May 1, 2024 • 1 min read

A Gentle Introduction to Deep Reinforcement Learning in JAX 🕹️ featured image

Reinforcement Learning

A Gentle Introduction to Deep Reinforcement Learning in JAX 🕹️

Published on Towards Data Science

Ryan Pégoud

• Nov 21, 2023 • 1 min read

Implementing a Transformer Encoder from Scratch with JAX and Haiku 🤖 featured image

Natural Language Processing

Implementing a Transformer Encoder from Scratch with JAX and Haiku 🤖

Published on Towards Data Science

Ryan Pégoud

• Nov 7, 2023 • 1 min read

Vectorize and Parallelize RL Environments with JAX: Q-learning at the Speed of Light⚡ featured image

Reinforcement Learning

Vectorize and Parallelize RL Environments with JAX: Q-learning at the Speed of Light⚡

Published on Towards Data Science

Ryan Pégoud

• Oct 15, 2023 • 1 min read