From a1eb756c0b7c03257637a21c66f0c88e8c1dd35c Mon Sep 17 00:00:00 2001 From: Julien Jerphanion Date: Mon, 15 Jun 2026 17:12:25 +0200 Subject: [PATCH] docs: Add instructions to install `llama.cpp` from conda-forge (#22219) * docs: Add instructions to install `llama.cpp` from conda-forge Signed-off-by: Julien Jerphanion * Rewording of instructions Co-authored-by: Georgi Gerganov --------- Signed-off-by: Julien Jerphanion Co-authored-by: Georgi Gerganov --- README.md | 2 +- docs/install.md | 32 ++++++++++++++++++++++++++++++-- 2 files changed, 31 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 41c904f39d..0652d13f29 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ LLM inference in C/C++ Getting started with llama.cpp is straightforward. Here are several ways to install it on your machine: -- Install `llama.cpp` using [brew, nix or winget](docs/install.md) +- Install `llama.cpp` using [brew, nix, winget, or conda-forge](docs/install.md) - Run with Docker - see our [Docker documentation](docs/docker.md) - Download pre-built binaries from the [releases page](https://github.com/ggml-org/llama.cpp/releases) - Build from source by cloning this repository - check out [our build guide](docs/build.md) diff --git a/docs/install.md b/docs/install.md index 7200bf9b7b..7198e61bf3 100644 --- a/docs/install.md +++ b/docs/install.md @@ -1,12 +1,40 @@ # Install pre-built version of llama.cpp -| Install via | Windows | Mac | Linux | -|-------------|---------|-----|-------| +| Install via | Windows | Mac | Linux | +|-------------|---------|------|-------| +| conda-forge | ✅ | ✅ | ✅ | | Winget | ✅ | | | | Homebrew | | ✅ | ✅ | | MacPorts | | ✅ | | | Nix | | ✅ | ✅ | +## conda-forge (Windows, Mac and Linux) + +conda-forge provides builds for: + - CUDA (Windows and Linux) + - Vulkan (Windows and Linux) + - Apple Metal (macOS) + +```sh +conda install -c conda-forge llama-cpp +``` + +```sh +mamba install -c conda-forge llama-cpp +``` + +```sh +# Project-local installation +pixi add llama-cpp + +# Global installation +pixi global install llama-cpp +``` + +This distribution is managed on [`conda-forge/llama-cpp-feedstock`](https://github.com/conda-forge/llama.cpp-feedstock/). + +Shall you have any problems, please open an issue on [its issue tracker](https://github.com/conda-forge/llama.cpp-feedstock/issues). + ## Winget (Windows) ```sh