Update Dockerfile

Dockerfile

@@ -1,4 +1,33 @@
-FROM ghcr.io/ggerganov/llama.cpp:full-cuda
+ARG UBUNTU_VERSION=22.04
+# This needs to generally match the container host's environment.
+ARG CUDA_VERSION=11.7.1
+# Target the CUDA build image
+ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
+# Target the CUDA runtime image
+ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
+
+FROM ${BASE_CUDA_DEV_CONTAINER} as build
+
+# Unless otherwise specified, we make a fat build.
+ARG CUDA_DOCKER_ARCH=all
+
+RUN apt-get update && \
+    apt-get install -y build-essential git
+
+WORKDIR /app
+
+COPY . .
+
+# Set nvcc architecture
+ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
+# Enable cuBLAS
+ENV LLAMA_CUBLAS=1
+
+RUN make
+
+FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
+
+COPY --from=build /app/main /main
 
 # Install build and runtime dependencies
 RUN apt-get update && \
@@ -9,8 +38,6 @@ RUN apt-get update && \
     pkg-config \
     curl
 
-RUN make LLAMA_CUBLAS=1
-
 RUN pip install -U pip setuptools wheel && \
   pip install --verbose llama-cpp-python[server]