Название: LLMOps: Managing Large Language Models in Production (Final Release)
Автор: Abi Aryan
Издательство: O’Reilly Media, Inc.
Год: 2025
Страниц: 450
Язык: английский
Формат: pdf, epub
Размер: 10.7 MB

Here's the thing about Large Language Models: they don't play by the old rules. Traditional MLOps completely falls apart when you're dealing with GenAI. The model hallucinates, security assumptions crumble, monitoring breaks, and agents can't operate. Suddenly you're in uncharted territory. That's exactly why LLMOps has emerged as its own discipline. LLMOps: Managing Large Language Models in Production is your guide to actually running these systems when real users and real money are on the line. This book isn't about building cool demos. It's about keeping LLM systems running smoothly in the real world. I’m writing this book to help you appreciate the unique aspects of the full LLM-based application lifecycle, from data engineering to model deployment and API design to monitoring, security, and resource optimization. I want to give you a strong foundation for making decisions as you build, maintain, and optimize your LLM data, models, and applications.

Название: Learning GitHub Copilot: Multiplying Your Coding Productivity Using AI
Автор: Brent Laster
Издательство: O’Reilly Media, Inc.
Год: 2025
Страниц: 350
Язык: английский
Формат: epub
Размер: 27.1 MB

Harness the power of Generative AI in your coding with GitHub Copilot. In this practical guide, author Brent Laster explains what Copilot is, how it works, and what it can do for you. You'll learn how to leverage AI to automate and simplify development, testing, documentation, and more. Software professionals in all roles will find the information needed to supercharge your productivity. "Learning GitHub Copilot" shows DevOps engineers, software developers, and database administrators how to make the most of the tool's code completion and generation capabilities. This book is for anyone who is trying to learn more about using AI assistants for developing software. Yes, it’s specifically about GitHub Copilot, but many of the examples and flows have parallels in other AI coding tools and environments. To get the most out of this book, you should already have experience coding in an IDE and have a basic knowledge of GitHub. To be clear, this book is not going to teach you how to code, how to use an IDE, or how to use GitHub. Whether you are a software developer, quality engineer, SRE, or someone who is just looking to understand how an AI assistant like Copilot can benefit them, I believe you’ll find meaningful information and insights.

Название: System Programming in Linux: A Hands-On Introduction
Автор: Stewart Weiss
Издательство: No Starch Press
Год: 2026
Страниц: 1051
Язык: английский
Формат: pdf (true)
Размер: 44.2 MB

Learn to write real Linux software—not just run it. Most programmers never learn how Linux really works. Why? Because system programming is rarely taught, and the tools can be intimidating without the right guidance. As a result, many developers stick to high-level languages and frameworks—writing code that runs on Linux without understanding how it interacts with Linux. In today’s world, that’s not enough to stand out. Especially as more companies turn to AI to write their software, the question becomes: How do you stay relevant in an AI-driven world? You learn how things really work. If you’ve ever wondered how processes are created, how memory and files are managed, or how programs communicate in a Unix environment, System Programming in Linux will make it all make sense. This is a hands-on guide to writing software that interfaces directly with the Linux operating system.

Название: Building Reliable AI Systems: Production-ready methods to reduce hallucination, bias, and more (MEAP v7)
Автор: Rush Shahani
Издательство: Manning Publications
Год: 2025
Страниц: 345
Язык: английский
Формат: pdf, epub
Размер: 16.1 MB

Tested strategies to reduce hallucinations, improve performance and cost efficiency, and reduce bias or unethical behavior in your LLMs outputs. Building Reliable AI Systems shows you exactly how to guide large language models from research prototypes to scalable, robust, and efficient production systems. From model training to maintenance, an engineer will find everything they need to work with LLMs in this one-stop guide. Building Reliable AI Systems is a comprehensive guide to creating LLM-based apps that are faster and more accurate. It takes you from training to production and beyond into the ongoing maintenance of an LLM. In each chapter, you’ll find in-depth code samples and hands-on projects—including building a RAG-powered chatbot and an agent created with LangChain. Deploying an LLM can be costly, so you’ll love the performance optimization techniques—prompt optimization, model compression, and quantization—that make your LLMs quicker and more efficient. For data scientists or software engineers confident in Python and NLP.

Название: A Mathematical Introduction to Data Science
Автор: Yi Sun, Rod Adams
Издательство: Springer
Год: 2025
Страниц: 486
Язык: английский
Формат: pdf (true), epub
Размер: 39.9 MB

This textbook provides a comprehensive foundation in the mathematics needed for Data Science for students and self-learners with a basic mathematical background who are interested in the principles behind computational algorithms in Data Science. It covers sets, functions, linear algebra, and calculus, and delves deeply into probability and statistics, which are key areas for understanding the algorithms driving modern Data Science applications. Readers are guided toward unlocking the secrets of algorithms like Principal Component Analysis, Singular Value Decomposition, Linear Regression in two and more dimensions, Simple Neural Networks, Maximum Likelihood Estimation, Logistic Regression and Ridge Regression, illuminating the path from mathematical principles to algorithmic mastery. It is designed to make the material accessible and engaging, guiding readers through a step-by-step progression from basic mathematical concepts to complex Data Science algorithms. This approach facilitates a smoother transition into more advanced topics. Examples in Python.

Название: Creational Design Patterns in C#: Building Flexible and Scalable Software
Автор: Vaskaran Sarcar
Издательство: Apress
Год: 2025
Страниц: 128
Язык: английский
Формат: pdf (true), epub (true), mobi
Размер: 10.1 MB

Unlock the power of design patterns to elevate your software architecture. This pocket book provides an in-depth guide to five essential creational design patterns, crucial for building robust, scalable, and maintainable applications in C#. With step-by-step implementation in C# and a focus on practical applications, this book will empower you to enhance your software solutions and sharpen your design skills. The book starts by covering the simple factory pattern first where you will learn object creation with clear, single-responsibility classes followed by the factory method pattern. Next, you will go through the prototype, singleton, and builder patterns. In the end, you will demonstrate dependency injection with real-life examples. For OOP, C# developers who want to learn and practice design patterns to upgrade their development skills.

Название: Mean Field Guided Machine Learning
Автор: Yuhan Kang, Hao Gao, Zhu Han
Издательство: Springer
Год: 2025
Страниц: 159
Язык: английский
Формат: pdf (true), epub
b]Размер[/b]: 17.45 MB

This book explores the integration of Mean Field Game (MFG) theory with Machine Learning (ML), presenting both theoretical foundations and practical applications. Drawing from extensive research, it provides insights into how MFG can improve various ML techniques, including Supervised Learning, Reinforcement Learning, and Federated Learning. In this book, we explore the intersection of Mean Field Game (MFG) theory and Machine Learning, an innovative approach that holds promise for addressing these pressing challenges. MFG theory, which models the collective behavior of large populations of interacting agents, provides powerful mathematical tools for simplifying and optimizing complex systems. By integrating MFG theory with ML, we can enhance the efficiency, scalability, and robustness of Machine Learning models, opening new avenues for research and application development. With case studies and real-world examples, this book serves as a guide for researchers and students in communications and networks seeking to harness MFG’s potential in advancing ML.

Название: Rails Scales!: Practical Techniques for Performance and Growth
Автор: Cristian Planas
Издательство: The Pragmatic Bookshelf
Год: May 2025 (Version: P1.0)
Страниц: 352
Язык: английский
Формат: pdf, epub (true)
Размер: 10.8 MB

Rails doesn't scale. So say the naysayers. They’re wrong. Ruby on Rails runs some of the biggest sites in the world, impacting the lives of millions of users while efficiently crunching petabytes of data. This book reveals how they do it, and how you can apply the same techniques to your applications. Optimize everything necessary to make an application function at scale: monitoring, product design, Ruby code, software architecture, database access, caching, and more. Even if your app may never have millions of users, you reduce the costs of hosting and maintaining it. Optimize every aspect of your Ruby on Rails applications for world-class performance. Tweak your Rails app for snappy responsiveness. Find bottlenecks that slow your code. Scale an app for massive data sets. This book introduces techniques, patterns, and tricks to make your Rails application become more performant and scale to billions of requests per day. Reading this book will help you make Rails applications that fly. And it will make you enjoy the process.

Название: Real-Time Machine Learning (MEAP v3)
Автор: Prema Roman, Patrick Deziel
Издательство: Manning Publications
Год: 2025
Страниц: 201
Язык: английский
Формат: pdf, epub
Размер: 10.1 MB

Build Machine Learning models that learn and update on the fly! Data changes fast in the real world, and traditional batch Machine Learning models often become stale as soon as they’re deployed. Updating them with the most current records can be tedious and expensive, making it more likely you’ll identify shifts and trends after the fact rather than responding to them as they happen. Real-Time Machine Learning shows you how to build ML systems that digest new data as it arrives, delivering accurate and relevant predictions even in environments where data changes rapidly. Real-Time Machine Learning reveals how to build models that learn while they operate in production environments. You’ll learn to use event-driven methodologies for real-time data processing and integrate online Machine Learning models into real-time data pipelines for responsive and adaptive applications. For data scientists and Machine Learning engineers experienced in Python.

Название: Гейм-дизайн: как создаются игры
Автор: Майкл Киллик
Издательство: Питер, Прогресс книга
Год: 2023
Страниц: 263
Язык: русский
Формат: pdf, fb2, epub, mobi
Размер: 12.1 MB

Узнайте, как придумать и создать свою первую игру. Загляните за кулисы гейм-дизайна и глубоко погрузитесь в теорию и техническую сторону разработки видеоигр. Книга затрагивает теорию гейм-дизайна, практические особенности реализации игр в различных жанрах, их внутренние механизмы и самые успешные проекты в конкурентном игровом мире. Майкл Киллик, получивший премию BAFTA за наставничество молодых дизайнеров видеоигр, познакомит вас с техническими аспектами разработки игр и поделится приемами, которые помогут сделать первые шаги на пути создания собственных проектов. Вы поймете особенности игровой индустрии и будете разбираться во всех этапах создания игрового продукта, от идеи до разработки и выпуска игры.