{
  "type": "edition",
  "site": {
    "name": "The Book Quiver",
    "language": "en-US",
    "url": "https://www.bookquiver.com"
  },
  "formats": "Every page has two versions with the same data: JSON (the page address + .json) and markdown (the page address + .md). Append .json or .md to any `url` in this document.",
  "title": "Generative AI on Kubernetes",
  "subtitle": null,
  "url": "https://www.bookquiver.com/roland-huss/generative-ai-on-kubernetes/9781098171926",
  "publisher": "O'Reilly Media",
  "publisher_series": [],
  "translators": [],
  "medium": "paper",
  "duration_seconds": null,
  "narrators": [],
  "illustrators": [],
  "cover_artists": [],
  "isbn": "978-10-9817-192-6",
  "pages": 250,
  "published": "2026-03-13",
  "language": "en_US",
  "cover": "https://quivercdn.com/covers/oreilly-media/roland-huss/generative-ai-on-kubernetes_978-10-9817-192-6-9e338015.webp?v=2026-11-08%2003%3A11%3A42",
  "json": "https://www.bookquiver.com/roland-huss/generative-ai-on-kubernetes/9781098171926.json",
  "markdown": "https://www.bookquiver.com/roland-huss/generative-ai-on-kubernetes/9781098171926.md",
  "binding": "Softcover",
  "description": "Generative AI is revolutionizing industries, and Kubernetes has fast become the backbone for deploying and managing these resource-intensive workloads. This book serves as a practical, hands-on guide for MLOps engineers, software developers, Kubernetes administrators, and AI professionals ready to combine AI innovation with the power of cloud native infrastructure. Authors Roland Huß and Daniele Zonca provide a clear road map for training, fine-tuning, deploying, and scaling GenAI models on Kubernetes, addressing challenges like resource optimization, automation, and security along the way. With actionable insights with real-world examples, readers will learn to tackle the opportunities and complexities of managing GenAI applications in production environments. Whether you're experimenting with large-scale language models or facing the nuances of AI deployment at scale, you'll uncover expertise you need to operationalize this exciting technology effectively. - Learn how to deploy LLMs more efficiently with optimized inference runtimes - Get hands-on with GPU scheduling, including hardware detection and multinode scaling - Monitor and understand LLM-specific metrics like Time to First Token and token throughput - Know when to fine-tune a model or when retrieval augmentation is the better choice - Discover how to evaluate models with standardized benchmarks before committing GPU resources - Learn to run agentic applications with secure tool integration, identity management, and persistent state",
  "book": {
    "title": "Generative AI on Kubernetes",
    "slug": "generative-ai-on-kubernetes",
    "url": "https://www.bookquiver.com/roland-huss/generative-ai-on-kubernetes"
  },
  "authors": [
    {
      "name": "Roland Huß",
      "slug": "roland-huss",
      "url": "https://www.bookquiver.com/roland-huss"
    },
    {
      "name": "Daniele Zonca",
      "slug": "daniele-zonca",
      "url": "https://www.bookquiver.com/daniele-zonca"
    }
  ]
}