Inference Engineering in Practice: Serving LLMs Fast and Cheap: Batching, KV Cache, Quantization, and the Cost of Every Token

Name: Inference Engineering in Practice: Serving LLMs Fast and Cheap: Batching, KV Cache, Quantization, and the Cost of Every Token
Brand: Independently Published
Price: 29.99 USD
Availability: InStock
Author: Gabriel Anhaia
ISBN: 9798175785631

by Gabriel Anhaia

$29.99Paperback

In stock, ships in 1-2 business days

Free standard shipping on orders over $40. ISBN 9798175785631

Details

Format: Paperback
ISBN-13: 9798175785631
Publisher: Independently Published
Published: September 20, 2026
Pages: 460
Weight: 21.4 oz
Subject: Computers

More by Gabriel Anhaia

All books

The Metacognition Method: How to Know What You Actually Know in the Age of AI cover

Popular in Computers

Browse Computers

The Book of Why: The New Science of Cause and Effect cover

Inference Engineering in Practice: Serving LLMs Fast and Cheap: Batching, KV Cache, Quantization, and the Cost of Every Token

Details

More by Gabriel Anhaia

The Metacognition Method: How to Know What You Actually Know in the Age of AI

O Método da Prática Deliberada: Por que a prática não leva à perfeição - e o que leva

PHP Desacoplado: Arquitetura Clean e Hexagonal para Aplicações que Sobrevivem ao Framework

Reading That Sticks: Why AI Can Summarize Any Book but Can't Make You Smarter

Zettelkasten: Come imparare davvero nell'era dell'IA: Un sistema per trasformare ciò che leggi in comprensione duratura

PHP Desacoplado en la Práctica: Arquitectura Clean y Hexagonal para aplicaciones que sobreviven al framework

Arquitectura Hexagonal en Go: Ports, Adapters y Servicios que Perduran

La Répétition Espacée: Quinze minutes par jour pour que ce que tu as appris soit encore là dans un an

Guía de bolsillo de agentes de IA: Patrones para construir sistemas autónomos con LLMs

KI-Agenten - Das Pocket-Handbuch: Patterns für den Bau autonomer Systeme mit LLMs

Observability para LLM Applications: Tracing, evals y deploy de IA en la que puedes confiar

Agentes en Producción: Construir, tracing y deploy de IA multipaso en la que puedes confiar

Popular in Computers

The Book of Why: The New Science of Cause and Effect

Fixing Tech: Make It Just Work

Mastering AI: A Survival Guide to Our Superpowered Future

Building Reliable AI Systems: Applications and Agents You Can Trust

My Coworker Is a Robot: Navigating the Technology That Could Replace You (or Earn Your Next Promotion)

Unbreakable: Secure Your Digital Life in a World Built to Breach You

The Craft of Post-Training: A Practical Guide for AI Engineers and Developers

Beginner's Step-By-Step Coding Course: Learn Computer Programming the Easy Way

The Well-Grounded Rubyist, Fourth Edition

Embedded AI: Intelligence at the Deep Edge

Build a Large Language Model (from Scratch)

On the Future of Species: Authoring Life by Means of Artificial Biological Intelligence