# Llama Forge RS App ![AGPL 3 or later](https://img.shields.io/badge/license-AGPL%203.0%20or%20later-blue) ![🚀 Blazingly fast](https://img.shields.io/badge/%F0%9F%9A%80%20blazingly-fast-brightgreen) ![🪨 Rock Solid](https://img.shields.io/badge/%F0%9F%AA%A8%20rock-solid-violet) ![Zero Bugs🪳](https://img.shields.io/badge/zero-bugs%20%F0%9F%AA%B3-red) ![yes it's](https://img.shields.io/badge/yes%20it's-brightgreen) ![Written in rust😎](https://img.shields.io/badge/written%20in-rust%20%F0%9F%98%8E-orange?logo=rust) ## Overview TODO Decide on projekt name, Llama Forge RS ? YALU ? ## Dependency Installation ### Via Nix Flake ```nix { inputs = { # ... + llama-cpp = { + url = "git+https://git.vlt81.de/tristan/llama.cpp.git"; + }; + # TODO Add nix pacakge for app itself }; outputs = { # .... + , llama-cpp , ... } @ inputs: let # Then just use the package, e.g. for home-manager + home.packages = [ inputs.llama-cpp.packages.${system}.rocm ]; + # This might be needed for some AMD GPUS + home.sessionVariables = { + HSA_OVERRIDE_GFX_VERSION = "10.3.0"; + }; } ``` ## License Notice TODO Add name hre Licensed under AGPL 3 or later, see [./LICENSE.md](./LICENSE.md) TODO one-liner project description here Copyright (C) 2023-2024 Tristan Druyen This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details. You should have received a copy of the GNU Affero General Public License along with this program. If not, see .