You can choose to run with Docker or Docker Compose. Both are not needed.
- Git
- Docker
- Docker Compose
- NVIDIA Container Toolkit (if using NVIDIA GPU)
Assumptions will be made on all of these values if you choose to skip this step. Create a .env file if one does not exist and modify it to your needs. Here is an example .env file:
LOCAL_LLM_API_KEY=
THREADS=10
GPU_LAYERS=0
MAIN_GPU=0LOCAL_LLM_API_KEY- The API key to use for the server. If not set, the server will not require an API key.THREADS- The number of threads to use. Default isyour CPU core count minus 1.
The following are only applicable to NVIDIA GPUs:
GPU_LAYERS- The number of layers to use on the GPU. Default is0.MAIN_GPU- The GPU to use for the main model. Default is0.
Make sure to move your .env file to the Local-LLM directory if you set one up.
git clone https://github.com/Josh-XT/Local-LLM
cd Local-LLM
docker-compose pull
docker-compose upYou must have the NVIDIA Container Toolkit installed if using NVIDIA GPU.
git clone https://github.com/Josh-XT/Local-LLM
cd Local-LLM
docker-compose -f docker-compose-cuda.yml pull
docker-compose -f docker-compose-cuda.yml up