Update Dockerfile

Dockerfile

@@ -1,37 +1,11 @@
-ARG UBUNTU_VERSION=22.04
-# This needs to generally match the container host's environment.
-ARG CUDA_VERSION=12.6.0
-# 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 ${BASE_CUDA_DEV_CONTAINER} AS build
-
-# CUDA architecture to build for (defaults to all supported archs)
-ARG CUDA_DOCKER_ARCH=default
-
-RUN apt-get update && \
-    apt-get install -y build-essential git cmake libcurl4-openssl-dev
-
-WORKDIR /app
-
-RUN git clone https://github.com/ggerganov/llama.cpp --depth 1 .
-
-# Use the default CUDA archs if not specified
-RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
-        export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
-    fi && \
-    cmake -B build -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} . && \
-    cmake --build build --config Release --target llama-server -j$(nproc)
-
-
-
+FROM ghcr.io/ggerganov/llama.cpp:server-cuda AS build
 FROM node:22 AS runtime
 
 RUN npm i -g http-server
 
 WORKDIR /app
-COPY --from=build /app/build/bin/llama-server /app/llama-server
+COPY --from=build /libggml.so /app/libggml.so
+COPY --from=build /libllama.so /app/libllama.so
+COPY --from=build /llama-server /app/llama-server
 
 CMD ["http-server", "/app", "-p", "7860", "-c-1"]