@runanywhere/llamacpp

Llama.cpp backend registration for the RunAnywhere React Native SDK — installs the native LLM/VLM provider; model lifecycle and inference live in @runanywhere/core.

Installation

npm install @runanywhere/[email protected] @runanywhere/[email protected]
cd ios && pod install && cd ..

See the React Native SDK README for platform setup.

Usage

import { RunAnywhere } from '@runanywhere/core';
import { LlamaCPP } from '@runanywhere/llamacpp';

await RunAnywhere.initialize();
await LlamaCPP.register();

const result = await RunAnywhere.generate('Write one sentence about local AI.');
console.log(result.text);

Register, download, and load models through @runanywhere/core. See the React Native SDK README.

Support

• React Native SDK documentation
• Discord
• [email protected]

License

RunAnywhere License. See LICENSE.