Fixed Cuda Dockerfile

Previously models produced garbage output when running on GPU with layers offloaded.

Similar to related fix on another repo: bartowski1182/koboldcpp-docker@331326a

Author: pradhyumna85

docker/cuda_simple/Dockerfile

@@ -4,13 +4,24 @@ FROM nvidia/cuda:${CUDA_IMAGE}
 # We need to set the host to 0.0.0.0 to allow outside access
 ENV HOST 0.0.0.0
 
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential \
+    python3 python3-pip gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
+
 COPY . .
 
-# Install the package
-RUN apt update && apt install -y python3 python3-pip
+# setting build related env vars
+ENV CUDA_DOCKER_ARCH=all
+ENV LLAMA_CUBLAS=1
+
+# Install depencencies
 RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings
 
-RUN LLAMA_CUBLAS=1 pip install llama-cpp-python
+# Install llama-cpp-python (build with cuda)
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
 
 # Run the server
 CMD python3 -m llama_cpp.server