# llama-cpp-binaries

**Repository Path**: mirrors_agronholm/llama-cpp-binaries

## Basic Information

- **Project Name**: llama-cpp-binaries
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: AGPL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-05-01
- **Last Updated**: 2026-06-20

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# llama-cpp-binaries

llama.cpp server in a Python wheel.

## Installation

```
git clone --recurse-submodules https://github.com/oobabooga/llama-cpp-binaries
cd llama-cpp-binaries
CMAKE_ARGS="-DGGML_CUDA=ON -DGGML_NATIVE=off -DCMAKE_CUDA_ARCHITECTURES=all" pip install -v .
```

## Usage

```python
import subprocess

from llama_cpp_binaries import get_binary_path

server_binary_path = get_binary_path()

# start with subprocess.Popen(...)
```