IndexMapAbout
Tool / RuntimeLLMCross-Modal

llama.cpp

Also known as: llamacpp · llama-server

Plain English

llama.cpp runs language models on local machines. It can be used from the command line, embedded in another program, or run as an API server.

Technical Overview

The C and C++ runtime uses ggml tensor operations and loads GGUF weights. It supports CPU and GPU backends, and smaller quantized weights can reduce memory requirements. Its multimodal library handles inputs such as images and audio for supported models.

Chronological Entries (3)

#1Milestone
AI-Assisted

The llama.cpp project merged a public C API for its multimodal library. Applications embedding the runtime gained a common interface for preparing and evaluating image inputs alongside text on supported models.

Direct Relations (2)