Author name: Rythmkumar

ai, deep-learning, Machine Learning, pytorch, stable-diffusion

Why My PyTorch Diffusion Model Was Slow — and How I Made It 3× Faster

Rythmkumar / March 25, 2026

Training a Diffusion Model — even on a “simple” dataset like MNIST — is a trial by fire for your hardware. You expect the GPU to do the heavy lifting, but more often than not, your expensive silicon is sitting idle, waiting for a sluggish pipeline to t…

Artificial Intelligence, data-science, llm, Machine Learning, naturallanguageprocessing

BERT vs. Transformers: A Complete Architectural and Mathematical Dissection

Rythmkumar / March 21, 2026

When I first read about BERT (Bidirectional Encoder Representations from Transformers), the number one question that plagued my mind was a simple definition issue.We are told BERT is “Bidirectional.” But wait — BERT is based on the Transformer Encoder….