Offer ends midnight PT May 10th. Only at manning.com.
Here's your opportunity to catch up on Manning's latest releases, MEAP updates, bestsellers and more! And don't forget: you always get the best deals at manning.com!
New MEAP! Quantization and Fast Inference
A practitioner’s guide to efficient AI
Today's AI models demand a lot of memory, compute, and server horsepower--which quickly translates into cost. Quantization and Fast Inference 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.
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. [Read more]
4 chapters of this new MEAP are available now with more to follow soon!
A friendly guide for programmers and other curious people
A “software architecture” defines the fundamental, high-level structure of a software system, acting as a blueprint for its components, their relationships, and how they interact. As a developer, having a command of the principles, patterns and vocabulary of software architecture empowers you to contribute meaningfully throughout an application’s lifecycle—from its initial design to its deployment in production.
Grokking Software Architecture is a fast-paced introduction to the foundational ideas of software architecture, written for developers and aspiring architects. Creative illustrations and diagrams,
