Rohit Kewalramani·Jun 9, 2025The Illusion of Thinking: A Critical Review of Apple’s Latest Research on Large Reasoning ModelsWhen AI “Thinking” Hits a Wall — A Data Scientist’s Perspective
Rohit Kewalramani·Sep 7, 2024Is your RAG doomed?Retrieval Augmented Generation follows an unusual story of RAGs to Riches (pun intended). Of late, there has been a flurry of new and…
Rohit Kewalramani·Feb 10, 2024Lag-Llama: A Potential Game Changer for Time Series Forecasting?As a longtime data scientist and practitioner in the field, I am always keeping an eye out for innovative techniques that could challenge…A response icon3A response icon3
Rohit Kewalramani·Jan 28, 2024Basics of Distributed Training — PyTorch editionAs deep learning models grow larger and more computationally intensive, training them on a single GPU or machine becomes very time and…
Rohit Kewalramani·Sep 24, 2023TGI vs. vLLM: Making Informed Choices for LLM DeploymentIn the world of deploying and serving Large Language Models (LLMs), two notable frameworks have emerged as powerful solutions: Text…A response icon4A response icon4