Inside DeepInfer: How an LLM Inference Engine Works Copyright (c) 2026 Jianxin Zhao. Book text and original illustrations Except where otherwise noted, the book's original text and illustrations, including the web and PDF editions, are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International licence (CC BY-NC-SA 4.0): https://creativecommons.org/licenses/by-nc-sa/4.0/ You may share, translate and adapt this material for noncommercial purposes under the licence's terms. Credit Jianxin Zhao and the book's title, retain the copyright and licence notices, link to the licence and identify changes. Shared adaptations must use the same or a compatible licence. The licence does not grant permission for commercial use; contact Jianxin Zhao for a separate commercial licence. This is a summary, not a replacement for the licence's legal terms: https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode.en Exceptions and limitations to copyright, such as quotation, fair use or fair dealing, remain unaffected. Code and third-party material The CC licence above does not apply to separately licensed code or third-party material. DeepInfer source excerpts remain under the Apache License 2.0, with their attribution and notices preserved in excerpts/LICENSE and excerpts/NOTICE.txt. The companion code is published under Apache-2.0 at: https://github.com/jzstark/inside-deepinfer-code Other third-party material remains subject to its own copyright and any applicable licence. Nothing in this notice reduces rights granted by those licences or by applicable law.