RSSAmplifier

Blog

Datta's Blog

Visual, math-backed explanations of LLM systems, attention, fine-tuning, GPU kernels, and the engineering details behind modern deep learning.

datta0.github.ioRSS feed ↗5 posts

Latest posts

Systems for LLM RL

Foray into the systems challenges and approaches for LLM RL

Reinforcement Learning for LLMs

A brief introduction to reinforcement learning for LLMs

The MathemaTricks behind FlashAttention

Fast and memory efficient exact attention

The lore behind LoRA

LoRA imagined from the ground up

Exploring the Mixture of Experts

An intuitive build up to Mixture of Experts