Skip to content

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Mobile Inference Landscape

A map of how neural networks actually run on the devices in our pockets, on our wrists, in our ears, and in our cars — the silicon, the software, the vendors, and the trade-offs that shape what ships.

41 chapters across 12 parts. ~148 pages.

What's in here

  • chapters/ — one markdown file per chapter, numbered 01-… through 41-….
  • outline.md — the working outline for the book, with design principles.
  • build_book.py — assembles all chapters into a single HTML and renders a PDF via headless Chrome.
  • mobile_inference_book.pdf — the built book.

Reading

The PDF is the intended reading format. If you'd rather read on GitHub, the chapter files are plain markdown and render cleanly.

Each chapter is designed to stand reasonably alone — dip in at a topic you care about — with explicit cross-references where prior context matters. The "What you need to remember" list at the end of each chapter is the TL;DR if you're scanning.

Structure

Part Chapters Topic
I 1 Context — why on-device, why now, what "mobile" means
II 2–5 Inference fundamentals — transformers, tokens, prefill/decode/KV, quantization
III 6–8 Mental models — the 8-layer stack, four ecosystems, central asymmetries
IV 9–12 Silicon — SoC anatomy, CPU, GPU, NPU
V 13–16 Hardware APIs and shaders — Vulkan, OpenCL, Metal, NPU SDKs
VI 17–21 Vendor stacks — Qualcomm, MediaTek, Google, Apple, IP vendors
VII 22–26 Runtimes — llama.cpp, LiteRT, ORT, Core ML + MLX, compiler runtimes
VIII 27–29 Models and formats — quantization schemes, language/vision, speech/image
IX 30–33 Engineering — memory, scheduling, LoRA/speculative, profiling
X 34–36 Platform layer — walled gardens, privacy/regulation, app stores
XI 37–39 Future — compiler convergence, open drivers, research frontiers
XII 40–41 Deep dives — llama.cpp internals, inference optimization playbook

Building the PDF

Requirements:

  • Python 3 with the markdown package (pip install markdown)
  • Google Chrome (used in headless mode for rendering)
python3 build_book.py

Output: mobile_inference_book.html (intermediate) and mobile_inference_book.pdf.

The build script handles cover, table of contents grouped by part, page numbering, and styling. Edit chapters in chapters/, re-run the script, and the PDF updates.

Design principles

  • Mechanism first, metaphor second. Every abstraction is cashed out in what the hardware actually does.
  • Opinionated but sourced. Claims cite runtimes, commits, benchmarks, vendor docs. Opinions are marked as such.
  • Real code, judiciously. Shader excerpts, ggml interfaces, delegate APIs — but only where the code shows something words cannot.
  • Current as of its time. The field moves fast. The book is dated (2026). Stable parts are structural; transient parts are marked transient.
  • Friendly to the dip-in reader. Every chapter stands reasonably alone.

License

Content: CC BY 4.0. Build scripts: MIT.

About

No description, website, or topics provided.

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages