Quantization and Fast Inference: A Practitioner's Guide to Efficient AI, (Paperback)

<b>Get the eBook free when you register your print book at Manning.</b> <p>Today's AI models demand a lot of memory, compute, and server horsepower--which quickly translates into cost. This book show you how you can optimize AI models without architectural redesigns or task-specific compression. It reveals practical techniques for quantization, systematically reducing numerical precision to achieve faster inference, lower memory usage, and cheaper deployment--all with minimal accuracy loss. </p><p>From quantization fundamentals to runtime packaging, the book gives you a complete and comprehensive overview of the full quantization pipeline. It starts by deriving quantization mapping from first principles, and then builds your knowledge and skill through techniques for production-tested PTQ and QAT workflows and a fully compressed deployment. You'll learn to apply post-training quantization to production models, run quantization-aware training using fake quantization and straight-through estimators, and handle subtle tradeoffs like activation outliers in LLMs, KV cache pressure, and sub-8-bit formats like NF4 and FP4. </p><p> <b>What's inside</b> </p><p> - Applying post-training quantization to production models<br> - Deploying efficiently on CPUs, edge devices, and mobile<br> - Framework-agnostic techniques and real cross-framework parity testing<br> - Flowcharts and checklists for efficient decision making </p><p><b>About the reader</b> </p><p> For ML engineers and researchers experienced in Python. </p><p> <b>About the author</b> </p><p> <b>Vivek Kalyanarangan</b> is an AI/ML architect, researcher, and educator with over twelve years of experience designing and deploying large-scale machine learning systems.</p>

• Quantization and Fast Inference: A Practitioner's Guide to Efficient AI, (Paperback)
• Author: Manning Publications
• ISBN: 9781633433915
• Format: Paperback
• Publication Date: 2026-12-29
• Page Count: 350