Directory Structure

This document provides an overview of how the llama.cpp documentation is organized.

content/llama-cpp/
    ├── index.md                       # Landing page & Overview
    ├── DIRECTORY_STRUCTURE.md         # Map of the docs
    ├── 1-installation/                # Setup & Backend-specifics
    │   ├── index.md                   # Installation overview + backend comparison
    │   ├── prerequisites.md           # Git, CMake, Build Tools, etc.
    │   ├── comparison.md              # Which backend to choose?
    │   ├── cpu-installation.md        # Standard build + pre-built binaries
    │   ├── cuda-installation.md       # NVIDIA GPU (CUDA) setup
    │   ├── amd-installation.md        # AMD GPU (HIP) setup
    │   ├── intel-installation.md      # Intel GPU (SYCL/oneAPI) setup
    │   └── vulkan-installation.md     # Universal GPU (Vulkan) setup
    ├── 2-configuration/               # Environment & Settings
    │   ├── environment-variables.md   # PATH setup & system vars
    │   └── optimization.md            # Quantization & performance tips
    ├── 3-inference/                   # Running models
    │   ├── model-formats.md           # GGUF, model selection, download methods
    │   ├── cli-usage.md               # CLI flags, examples, complete reference
    │   ├── advanced-flags.md          # Deep dive into all inference parameters
    │   ├── prompt-templates.md        # Chat templates (Alpaca, Llama-3, etc.)
    │   └── llama-server.md            # HTTP API server & Web UI guide
    ├── 4-advanced/                    # Advanced techniques
    │   ├── index.md                   # Section overview
    │   ├── model-conversion.md        # Hugging Face → GGUF conversion
    │   └── speculative-decoding.md    # Faster inference with draft models
    ├── 5-troubleshooting/             # Common issues & fixes
    │   ├── index.md                   # Section overview
    │   └── common-issues.md           # Detailed solutions for build & runtime errors
    └── 6-references/                  # External links & resources
        └── external-resources.md      # Official repo, docs, SDK links, community

How to Navigate

• Installation: Start here if you are setting up your environment for the first time.
• Configuration: Use these guides if you need to fine-tune your performance or environment.
• Inference: Go here once you have a built llama.cpp and want to start chatting with models.
• Advanced: Dive into model conversion and speculative decoding once you’re comfortable.
• Troubleshooting: Check here if something isn’t working.
• References: Use these for official documentation and additional learning.

---

Last Updated: 2026-07-19