Archive - Prasad Z

From Tokens to Tensors: An Engineer's Deep Dive into LLM Inference Performance

Moving beyond the API: How understanding the silicon-level processing can shave seconds off your inference latency

Apr 26 • Prasad Z

February 2022

How to deploy Kubeflow on AWS EKS

This article is aimed at anyone who is trying to install Kubeflow on AWS.

Feb 4, 2022 • Prasad Z

December 2021

MLOps: Build ML lifecycle from scratch

Following continuous software engineering practices, there has been an increasing interest in rapid deployment of machine learning (ML) features, called…

Dec 15, 2021 • Prasad Z

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts