Inference Engineering

vLLM and SGLang, side by side. Learn how LLM serving works, measure both engines fairly, tune them with evidence, and take a model from an empty GPU to a deployment with a cost per million tokens you can defend.

Take control of your own AI infrastructure. Learn how to find, deploy and run uncensored LLMs on rented GPU servers, from choosing the right models and hardware to configuring inference engines and scaling APIs. Packed with practical guidance and real-world tools, this book shows you how to build powerful private AI deployments without unnecessary restrictions.

What if a 125B-parameter AI model could run locally on a gaming GPU with just 12 GB of VRAM? Strata makes it possible. This book takes you inside the techniques that make it work, from MoE sparsity and memory tiers to PCIe pipelining and speculative decoding, then shows you how to install, tune and troubleshoot it yourself.

Inference engineering is now its own discipline, with unique challenges around speed, cost, reliability and scale. This practical guide takes you from core concepts to production systems, showing how modern inference architectures work, how to optimize them and how to make better engineering decisions through measurement and trade-off analysis.