Systems Architecture & AI Engineering
Architecting High-Throughput Distributed Infrastructure & AI Platforms.
Welcome to my personal notebook and technical publication space. Here I share long-form essays, system architecture breakdowns, and ongoing explorations in distributed systems, foundation model platforms, and scalable engineering.
#AI Infrastructure
Oct 2026 • 14 min read
How LLM Inference Works: From Prompt to Generated Tokens
A practical walkthrough of tokenization, transformer execution, prefill and decode, KV-cache reads and writes, and the serving techniques behind vLLM.
Read the full article →
New