Open Gitclop opened 8 months ago
Found my Error. I use Pycharm with a virtual environment. Setting the environment variables from the terminal did not work, but setting them inside the pycharm settings >Tools > Terminal did the trick.
Found my Error. I use Pycharm with a virtual environment. Setting the environment variables from the terminal did not work, but setting them inside the pycharm settings >Tools > Terminal did the trick.
Setting environment variables does work. This could be an end-user error. You may not be activating the virtual environment from inside the terminal.
python -m virtualenv XXX
.\XXX\Scripts\activate
python -m pip install --upgrade poetry
python -m poetry install --with ui,local
python -m poetry install --extras chroma
python -m poetry run python scripts/setup
$env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'; poetry run pip install llama-cpp-python --force-reinstall --no-cache-dir
make run
I followed the readme, but i can't get llama-cpp to run on my 4090.
I am running python 3.10, latest cuda drivers and tried different llama-cpp verisons. In generell the gpu offloading works on my system (sentence-transformers runs perfectly on gpu) only llama-cpp is giving me trouble.