Search Results for "llama.cpp"

qvac-fabric-llm.cpp is a cross-platform large language model inference and fine-tuning engine built as an advanced fork of llama.cpp, designed to run efficiently across desktops, mobile devices, and heterogeneous GPU environments. The project focuses on removing hardware limitations traditionally associated with LLM deployment by enabling support for a wide range of backends, including Vulkan, Metal, CUDA, and CPU, making it accessible on devices ranging from smartphones to enterprise servers. ...

...Built as a standalone application without heavy dependencies, it emphasizes simplicity, portability, and ease of setup across multiple platforms including desktop and mobile environments. The tool supports local models such as Ollama and llama.cpp for fully offline operation, while also allowing integration with cloud APIs like OpenAI and Anthropic for access to more advanced capabilities. A key differentiator is its optional encryption of chat history and assets, ensuring that sensitive data can remain secure even when stored locally. Conversations are managed as local JSON files, giving users transparency and direct control over their data. ...