Update Dockerfile

Dockerfile

@@ -1,11 +1,7 @@
 ARG UBUNTU_VERSION=22.04
-ARG CUDA_VERSION=12.3.1
-ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
-ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
+ARG BASE_CPU_CONTAINER=ubuntu:${UBUNTU_VERSION}
 
-FROM ${BASE_CUDA_DEV_CONTAINER} as build
-
-ARG CUDA_DOCKER_ARCH=all
+FROM ${BASE_CPU_CONTAINER} as build
 
 RUN apt-get update && \
     apt-get install -y build-essential git cmake wget
@@ -16,8 +12,8 @@ RUN git clone https://github.com/ggerganov/llama.cpp.git
 
 WORKDIR /build/llama.cpp
 
-ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
-ENV LLAMA_CUBLAS=1
+# Ensure that LLAMA_CUBLAS is not set to 1
+ENV LLAMA_CUBLAS=0
 
 RUN mkdir build && \
     cd build && \
@@ -27,8 +23,7 @@ RUN mkdir build && \
 WORKDIR /data
 RUN wget https://huggingface.co/brunopio/Llama3-8B-1.58-100B-tokens-GGUF/resolve/main/Llama3-8B-1.58-100B-tokens-TQ2_0.gguf -nv -O model.gguf
 
-FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
-
+FROM ${BASE_CPU_CONTAINER} as runtime
 
 WORKDIR /app