llmedge-examples and llmedge
The examples repository provides usage demonstrations for the Android native AI inference library, making them ecosystem siblings where one serves as educational documentation for the other.
About llmedge-examples
Aatricks/llmedge-examples
Examples using the llmedge library
Delivers comprehensive on-device ML inference for Android through the llmedge library, supporting text generation, RAG pipelines, vision models, image/video synthesis, and speech processing (STT/TTS) with GPU acceleration via OpenCL/Vulkan. Uses a modular activity-based architecture demonstrating production patterns for GGUF model loading, ONNX embeddings, streaming inference, and resource management. Integrates Hugging Face Hub for model downloads, Google ML Kit for OCR, and supports popular models like SmolLM, Llava, Stable Diffusion, Wan, Whisper, and Bark.
About llmedge
Aatricks/llmedge
Android native AI inference library, bringing gguf models and stable-diffusion inference on android devices, powered by llama.cpp and stable-diffusion.cpp
Integrates **Whisper.cpp** and **Bark.cpp** for speech inference, with optional GPU acceleration via OpenCL/Vulkan backends; provides native KV-cache optimization and streaming text generation via JNI bindings. Supports multimodal workflows including on-device RAG with PDF indexing, vision models (LLaVA-style), Stable Diffusion with LoRA, and video generation (Wan 2.1), all coordinated through the instance-based `LLMEdge` facade for explicit resource management.
Scores updated daily from GitHub, PyPI, and npm data. How scores work