llama.cpp (llm/llama.cpp) Updated: 4 days, 22 hours ago Add to my watchlist

LLM inference in C/C++

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide variety of hardware - locally and in the cloud.

Version: 0.4.0 License: MIT

GitHub

Maintainers	i0ntempest
Categories	llm
Homepage	https://github.com/ggerganov/llama.cpp
Platforms	darwin
Variants	blas (Use ggml with BLAS support) debug (Enable debug binaries) gui (install the Qt-based gguf-editor-gui script) metal (Use ggml with Metal support) model_converters (install extra model conversion Python scripts) native (Use ggml optimized for the build host CPU) opencl (Use ggml with OpenCL support) openmp (Use ggml with OpenMP support) universal (Build for multiple architectures) vulkan (Use ggml with Vulkan support)

"llama.cpp" depends on

lib (2)

curl

ggml

build (3)

clang-20

cmake

pkgconfig

Ports that depend on "llama.cpp"

run (1)

ollama

Port Health:

Loading Port Health

llama.cpp (llm/llama.cpp) Updated: 4 days, 22 hours ago Add to my watchlist

"llama.cpp" depends on

lib (2)

build (3)

Ports that depend on "llama.cpp"

Port Health:

Installations (30 days)

30

Requested Installations (30 days)

20

llama.cpp (llm/llama.cpp) Updated: 4 days, 22 hours ago Add to my watchlist 5

"llama.cpp" depends on

lib (2)

build (3)

Ports that depend on "llama.cpp"

Port Health:

Installations (30 days)

30

Requested Installations (30 days)

20

llama.cpp (llm/llama.cpp) Updated: 4 days, 22 hours ago Add to my watchlist