Update Dockerfile

Dockerfile

@@ -30,11 +30,11 @@ RUN apt-get update && \
     # ffmpeg 
     # software-properties-common
 
-# RUN add-apt-repository ppa:longsleep/golang-backports && \
-#     apt-get update && \
-#     apt-get upgrade -y && \
-#     apt-get install -y --no-install-recommends ca-certificates \
-#     golang-go 
+# RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
+# RUN dpkg -i cuda-keyring_1.1-1_all.deb
+# RUN apt-get update
+# RUN apt-get -y install cuda-toolkit-12-4
+
 RUN curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama
 RUN chmod +x /usr/bin/ollama
 
@@ -71,11 +71,12 @@ RUN python -m pip install "huggingface-hub" "hf-transfer" "gradio[oauth]>=4.28.0
     # go build . --verbose \
     # go install . --verbose
     
-RUN git clone https://github.com/ggerganov/llama.cpp
+RUN git clone https://github.com/ggerganov/llama.cpp; exit 0
 
 WORKDIR ${APPDIR}/llama.cpp
+RUN git pull
 RUN python -m pip install -r requirements.txt
-RUN LLAMA_CUDA=0 make -j llama-quantize --verbose
+RUN GGML_CUDA=1 make -j llama-quantize --verbose
     
 # ENV PYTHONPATH=${APPDIR}/.venv/bin \
 ENV PYTHONUNBUFFERED=1 \