flutter_llama 0.1.1

Flutter plugin for running LLM inference with llama.cpp and GGUF models on Android and iOS

Changelog

0.1.1 - 2025-10-21

Added

• Comprehensive test suite with 71 unit tests
• Integration tests with Ollama model support
• Dynamic GGUF model loading utilities
• GitHub Actions CI/CD workflow
• Makefile for common development tasks
• Extensive testing documentation

Improved

• Added macOS platform support
• Enhanced documentation with testing guides
• Better error handling in tests
• Code formatting and linting

0.1.0 - 2025-10-21

Added

• Initial release of flutter_llama
• Support for GGUF model loading
• Blocking text generation API
• Streaming text generation API
• GPU acceleration support (Metal on iOS, Vulkan on Android)
• Configurable model parameters (threads, GPU layers, context size, etc.)
• Configurable generation parameters (temperature, top-p, top-k, etc.)
• Model info retrieval
• Stop generation functionality
• Full iOS (Swift) implementation
• Full Android (Kotlin + JNI) implementation
• Comprehensive documentation and examples

Features

• Native llama.cpp integration
• High-performance inference
• Cross-platform support (iOS and Android)
• Easy-to-use Dart API
• Production-ready code with error handling