Ankush Sharma | Observability for Large Language Models. Site Reliability and Chaos Engineering for AI at Scale (2026) [PDF, EPUB]
Автор: Ankush Sharma
Издательство: Apress
ISBN: 979-8-8688-2827-0, 979-8868828263
Жанр: Statistics, Artificial Intelligence, Software Development
Язык: Английский
Формат: PDF, EPUB
Качество: Изначально электронное (ebook)
Иллюстрации: Цветные и черно-белые
Описание:This book is a comprehensive guide designed to equip engineers, data scientists, and AI practitioners with the principles, tools, and strategies needed to ensure reliability, performance, and accountability in Large Language Models (LLMs).
The book begins by laying the groundwork with the foundations of observability, introducing LLMs, their significance in modern AI, and the critical role observability plays in maintaining robust systems. It then explores SRE principles, service level objectives, and incident response, while distinguishing the unique observability challenges that arise in AI and ML systems. Building on this foundation, the book dives into measuring performance, from defining SLOs tailored for LLMs to monitoring computational and token-level metrics. Readers gain practical insights into structured logging, debugging, and distributed tracing methods that provide visibility into complex LLM workflows. Scaling challenges are addressed through strategies for cross-model observability, autoscaling, latency reduction, and fault-tolerant infrastructure design. The book further explores chaos engineering, guiding readers through resilience testing in LLMs and the automation of chaos experiments in CI/CD pipelines. Finally, it highlights monitoring, retraining, and ethical considerations in AI observability, including governance, privacy, and accountability.
In conclusion, this book provides a holistic roadmap to building reliable, transparent, and future-ready LLM systems.
What you will learn:
How to design observability pipelines for LLMs, including token-level logging, prompt tracing, and
latency analysis.
Techniques for applying chaos engineering principles to test LLM robustness under stress and
failure scenarios.
Methods for building SLOs, SLAs, and dashboards tailored to inference quality and model
reliability.
Strategies for monitoring hallucinations, drift, bias, and ethical failures in real-time.
Who this book is for:
This book is for AI infrastructure engineers, SREs, machine learning platform teams, and applied AI practitioners deploying or maintaining LLM-based applications.
About the Author xxi
About the Technical Reviewer xxiii
Acknowledgments xxv
Introduction xxvii
Part I: Foundations of Observability for LLMs 1
Chapter 1: Introduction to LLM Systems 3
Chapter 2: Site Reliability Engineering (SRE) Overview 13
Chapter 3: Observability in AI vs. Traditional Systems 21
Part II: Measuring Performance in LLMs 29
Chapter 4: Defining Service Level Objectives (SLOs) for LLMs 31
Chapter 5: Observability Metrics for LLMs 43
Chapter 6: The Role of Logs in LLM Systems 51
Chapter 7: Distributed Tracing for LLM Pipelines 61
Part III: Scaling Observability Across Distributed Systems 69
Chapter 8: Observability in Multi-Model Environments 71
Chapter 9: Capacity Planning and Scaling LLMs 81
Chapter 10: Reducing Latency in LLM Systems 89
Chapter 11: Fault-Tolerant LLM Infrastructure 99
Part IV: Chaos Engineering for LLM Reliability 109
Chapter 12: Introduction to Chaos Engineering 111
Chapter 13: Chaos Experiments for LLMs 121
Chapter 14: Automating Chaos Engineering for AI 133
Part V: Monitoring and Improving LLM Performance 145
Chapter 15: Real-Time Monitoring Systems for LLMs 147
Chapter 16: Postmortems for LLM Failures 155
Chapter 17: Retraining and Model Drift Monitoring 163
Part VI: AI Ethics and Accountability in Observability 171
Chapter 18: Governance and Compliance in LLM Systems 173
Chapter 19: Telemetry and Accountability 183
Chapter 20: The Future of AI Observability 193
Appendix: The AI Reliability Engineer’s Field Manual 201
Index 229
Скриншоты:
Время раздачи: с 10 до 20 (минимум до появления первых 3-5 скачавших) 
