I enjoy keeping a record of everything. Whenever I get time, I try to document my ideas, experiences and many have found them helpful. This inspired me to share them as articles on my website. I write articles on various topics, ranging from foundational concepts to emerging trends within my field I read or find interesting, as well as career/guidance articles . . .

Blogs

Continuous Batching: Getting More LLM Throughput From the Same GPU

Paged KV Cache on Apple Silicon: Fixing Memory Fragmentation Without CUDA

From Naive Decode to KV Cache: Why LLM Serving Gets Faster With One Idea

System Design 04: Designing an LLM Chat Product With Memory and Context Management

System Design 03: Designing a RAG Pipeline for 10 Million Documents With Near-Zero Hallucination

System Design 02: Designing a RAG-based Q&A System Over Company Docs

System Design 01: Designing a Delivery app with AI features for salesmen

RAG Observability and Latency Analysis using BetterDB

AWS Nuke - The AWS Resources Destroyer

UV & Modern Python Dependency Management

Kubernetes Project Workflow - Commands & Mental Model

Dynamic Programming Patterns - Non Adjacent Selection DP

Open Source Contribution - Beginner's Guide

RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering

ConSens: Assessing Context Grounding in Open‑Book Question Answering

IELTS - How I Prepared / Preparation Guide & Materials

An Introduction to Self Supervised Learning (SSL)