Does ist matter on which hardwaer I install llama-cpp-python ?

[rsoika]

I am using llama-cpp-python with a Docker image based on nvidia/cuda

I build my Docker image usually on my notebook without a GPU with a Dockerfile like this:

ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
FROM nvidia/cuda:${CUDA_IMAGE}
RUN apt-get update && apt-get upgrade -y \
    && apt-get install -y build-essential python3 python3-pip gcc 
ENV CUDA_DOCKER_ARCH=all
ENV LLAMA_CUBLAS=1
RUN python3 -m pip install --upgrade pip pytest cmake fastapi uvicorn
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install --upgrade llama-cpp-python

Later I run this docker image on my sever with a GeForce GTX 1080 and Nvida/CUBA installed

My question is: Does it matter where I build this Docker image? Would it be more clever to build it on the GPU Server that later will run this image? Or is this install script independent form the hardware?