fix(docker): replace CPU wheel with official CUDA wheel for GPU inference

fix(docker): install prebuilt llama-cpp-python wheel directly to prevent build timeout

feat: re-add compilers to natively build llama-cpp-python from source

chore: optimize Dockerfile comments and configure persistent HF cache

fix: Implement pre-built manylinux wheels

Fix cache bug: Introduce cache buster to force fresh cmake build

Fix libc.musl error: Build llama-cpp natively with cmake for Debian

Fix: Downgrade Base-Image to Python 3.10 in Dockerfile

build: add streamlit theme ENV variables

build: include .streamlit config in docker image

fix: implement robust absolute paths for avatar and fix UI rendering

fix: match python version to codespace and resolve core conflict

fix: Streamlit Port auf 7860 für Hugging Face angepasst

Direkter Push der App zu Hugging Face