vLLM Part 1: PagedAttention & the LLM Serving Problem

How vLLM Rethinks Memory Management to Serve LLMs at Scale

Posted on May 1, 2025

Large language models are transforming every corner of software, but serving them in production is brutally expensive. A single LLaMA-13B model can consume over 26 GB of GPU memory just for its weights, and that is before accounting for the memory needed to actually process requests. When dozens or hundreds... [Read More]
Tags: vLLM LLM Inference Deep Learning Model Serving

Quantization with BitsAndBytes: Running Large Models on Consumer Hardware

A practical guide to model quantization using Hugging Face, bitsandbytes, and accelerate

Posted on March 10, 2025

Large language models have grown at a staggering pace. Models like LLaMA-2 70B carry 70 billion parameters, which in full 32-bit floating point precision would require roughly 280 GB of GPU memory just to load the weights. Even a 7B parameter model needs around 28 GB in FP32. For most... [Read More]
Tags: Quantization LLM Hugging Face Deep Learning Model Optimization

A/B Testing Part 3: Execution & Decision-Making

From Running Experiments to Making Confident Deployment Decisions

Posted on February 24, 2025

In Part 1 we covered experiment design fundamentals, and in Part 2 we explored the statistical framework and metric selection. In this final part, we tackle the practical realities of running experiments — the pitfalls that can invalidate your results, the infrastructure needed to run experiments reliably, and the decision-making... [Read More]
Tags: AB Testing Model Evaluation Experimental Design Statistical Testing Machine Learning

A/B Testing Part 2: Statistical Framework & Metrics

Choosing the Right Metrics and Statistical Foundations for A/B Tests

Posted on February 22, 2025

In Part 1 we covered the foundations of A/B testing: what it is, why it matters, and how to design experiments with proper user segmentation and traffic allocation. Now we turn to the statistical machinery that makes A/B testing rigorous — how to determine sample sizes, choose the right metrics,... [Read More]
Tags: AB Testing Model Evaluation Experimental Design Statistical Testing Machine Learning

A/B Testing Part 1: Foundations & Experiment Design

Model Evaluation in the Wild: A Practical Guide to A/B Testing

Posted on February 20, 2025

In the high-stakes world of machine learning deployment, launching a new model is like piloting a spacecraft - every decision matters, and there’s no room for blind leaps of faith. Enter A/B testing, the mission control center of model deployment that transforms uncertainty into calculated progress. Think of A/B testing... [Read More]
Tags: AB Testing Model Evaluation Experimental Design Statistical Testing Machine Learning

Mathematical modeling of Infectious disease spread

Essential concepts related to infectious disease modeling

Posted on May 15, 2020

With the recent pandemic disease caused by covid-19 virus, it is important to develop models that can better monitor how the disease will be propagated with time. We can check the total Covid cases that have occurred across the world from Jan 2020 till present day. This will provide a... [Read More]
Tags: Compartmental-based modeling Infectious disease Covid-19 Pandemic Resources

Particles and Quantum mechanics

Essential concepts related to particle physics

Posted on August 5, 2019

In this post, fundamental concepts related to subatomic particles and quantum mechanics are presented. The objective of this post is to provide you a clear and precise understanding of topics related to quantum mechanics, quantum fields and taxonomy of particles. But before, delving into more on these topics, take a... [Read More]
Tags: Particles Physics Quantum mechanics Quantum fields Uncertainty Principle Resources

Blockchain and cryptocurrency

Understanding the essential concepts of blockchain and cryptocurrency

Posted on April 18, 2018

Business networks today are often inefficient because each participant in the network keeps records, or a ledger, of all transactions between all the parties that the business interacts with. This process is expensive because of duplication of effort and intermediaries adding costs for their services. One solution to this problem... [Read More]
Tags: Blockchain Bitcoin Cryptocurrency Fundamentals Resources