mdrokz/rust-llama.cpp
Rust language bindings for llama.cpp enabling efficient LLM model inference from Rust.
Velocity · 7d
+0.4
★ / day
Trend
→steady
star history
This repository provides Rust FFI bindings to llama.cpp, a C/C++ library optimized for running large language models with quantization. It allows Rust developers to load GGML/GGUF format models and run inference with configurable options including GPU acceleration via Metal, CUDA, and OpenCL backends.