llama.cpp (Forked for Android/Termux Optimization)

이 프로젝트는 ggerganov/llama.cpp를 포크한 저장소입니다. 주요 목적은 Android(Termux) 환경에서 LLM(Large Language Model)을 효율적으로 구동하기 위한 빌드 최적화 및 성능 테스트입니다.

LLM inference in C/C++

📌 출처 및 원본 프로젝트 (Original Source)

모든 핵심 소스 코드와 로직의 저작권은 원본 작성자에게 있습니다. 원본 프로젝트에 대한 상세한 정보와 최신 업데이트는 아래 링크를 참조하세요.

• Original Repository: https://github.com/ggerganov/llama.cpp
• Original README: View Original Documentation
• License: MIT License

---

📱 현재 타겟 환경 (Target Environment)

본 포크 저장소는 특히 아래의 하드웨어 사양에 최적화된 빌드 환경을 구성하는 데 집중하고 있습니다.

• Device: Samsung Galaxy Fold 3
• Processor: Qualcomm Snapdragon 888
• GPU: Adreno 660 (Vulkan / OpenCL 지원 테스트)
• Memory: 12GB RAM
• OS: Android (Termux 환경)

---

🛠️ 주요 수정 및 테스트 사항 (Work in Progress)

원본 프로젝트를 바탕으로 다음 항목들을 중점적으로 다룹니다.

1. Build Optimization: Termux 내에서 CPU 전용, Vulkan 및 OpenCL 백엔드 빌드 시 발생하는 오류 해결.
2. Performance Tuning: Snapdragon 888의 Adreno GPU를 활용한 추론 속도 최적화.
3. Model Compatibility: GGUF 형식의 다양한 모델(Gemma, Qwen, Llama 등) 구동 테스트.

---

🚀 빠른 시작 (Quick Start)

Termux 환경에서의 기본적인 빌드 절차는 다음과 같습니다 (원본 가이드 준수).

• Hugging Face cache migration: models downloaded with -hf are now stored in the standard Hugging Face cache directory, enabling sharing with other HF tools.
• guide : using the new WebUI of llama.cpp
• guide : running gpt-oss with llama.cpp
• [FEEDBACK] Better packaging for llama.cpp to support downstream consumers 🤗
• Support for the gpt-oss model with native MXFP4 format has been added | PR | Collaboration with NVIDIA | Comment
• Multimodal support arrived in llama-server: #12898 | documentation
• VS Code extension for FIM completions: https://github.com/ggml-org/llama.vscode
• Vim/Neovim plugin for FIM completions: https://github.com/ggml-org/llama.vim
• Hugging Face Inference Endpoints now support GGUF out of the box! ggml-org#9669
• Hugging Face GGUF editor: discussion | tool
• WebGPU support is now available in the browser, see a blog/demo introducing it here.

manifesto / ggml / ops / maintainer PRs / compile times / lib llama API / llama-server REST API

ggml / ops / maintainer PRs / dev stats / lib llama API / llama-server REST API

Quick start

A few options to get llama.cpp installed on your machine:

• Visit https://llama.app and follow the instructions
• Run with Docker - see our Docker documentation
• Download pre-built binaries from the releases page
• Build from source by cloning this repository - check out our build guide

Once installed:

# Download and run a model directly from Hugging Face
llama cli -hf ggml-org/Qwen3.5-0.8B-GGUF

# Launch OpenAI-compatible API server
llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF

VLM session with llama cli

Built-in web UI against llama serve

Description

The main goal of llama.cpp is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

• Plain C/C++ implementation without any dependencies
• Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
• AVX, AVX2, AVX512 and AMX support for x86 architectures
• RVV, ZVFH, ZFH, ZICBOP and ZIHINTPAUSE support for RISC-V architectures
• 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
• Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads GPUs via MUSA)
• Vulkan and SYCL backend support
• CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity

The llama.cpp project is build on top of the ggml library.

Supported backends

Backend	Target devices
BLAS	All
BLIS	All
CANN	Ascend NPU
CUDA	Nvidia GPU
HIP	AMD GPU
Hexagon	Snapdragon
IBM zDNN	IBM Z & LinuxONE
MUSA	Moore Threads GPU
Metal	Apple Silicon
OpenCL	Adreno GPU
OpenVINO [In Progress]	Intel CPUs, GPUs, and NPUs
RPC	All
SYCL	Intel GPU
VirtGPU	VirtGPU APIR
Vulkan	GPU
WebGPU	All
ZenDNN	AMD CPU

Documentation

Tools

• cli
• completion
• server
• GBNF grammars

Development

• How to build
• Running on Docker
• Build on Android
• Multi-GPU usage
• Performance troubleshooting
• GGML tips & tricks
• XCFramework
• Completions
• Models
• Release process

Contributing

• Contributors can open PRs
• Collaborators will be invited based on contributions
• Maintainers can push to branches in the llama.cpp repo and merge PRs into the master branch
• Any help with managing issues, PRs and projects is very appreciated!
• Read the CONTRIBUTING.md for more information

XCFramework

The XCFramework is a precompiled version of the library for iOS, visionOS, tvOS, and macOS. It can be used in Swift projects without the need to compile the library from source. For example:

// swift-tools-version: 5.10
// The swift-tools-version declares the minimum version of Swift required to build this package.

import PackageDescription

let package = Package(
    name: "MyLlamaPackage",
    targets: [
        .executableTarget(
            name: "MyLlamaPackage",
            dependencies: [
                "LlamaFramework"
            ]),
        .binaryTarget(
            name: "LlamaFramework",
            url: "https://github.com/ggml-org/llama.cpp/releases/download/b5046/llama-b5046-xcframework.zip",
            checksum: "c19be78b5f00d8d29a25da41042cb7afa094cbf6280a225abe614b03b20029ab"
        )
    ]
)

The above example is using an intermediate build b5046 of the library. This can be modified to use a different version by changing the URL and checksum.

Completions

Command-line completion is available for some environments.

Bash Completion

Acknowledgements

• yhirose/cpp-httplib - Single-header HTTP server, used by llama-server - MIT license
• nothings/stb - Single-header image format decoder, used by multimodal subsystem - Public domain
• nlohmann/json - Single-header JSON library, used by various tools/examples - MIT License
• mackron/miniaudio - Single-header audio format decoder, used by multimodal subsystem - Public domain
• sheredom/subprocess.h - Single-header process launching solution for C and C++ - Public domain