ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04

FROM docker.io/intel/deep-learning-essentials:${ONEAPI_VERSION} as base

ARG intel_arch=bmg_g21
ARG IGC_VERSION=v2.30.1
ARG IGC_VERSION_FULL=2_2.30.1+20950
ARG COMPUTE_RUNTIME_VERSION=26.09.37435.1
ARG COMPUTE_RUNTIME_VERSION_FULL=26.09.37435.1-0
ARG IGDGMM_VERSION=22.9.0
RUN --mount=type=cache,destination=/tmp/neo \
  cd /tmp/neo && wget -c \
  https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
  https://github.com/intel/intel-graphics-compiler/releases/download/${IGC_VERSION}/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  && dpkg --install *.deb

FROM base as build

RUN --mount=type=cache,destination=/var/lib/apt \
  --mount=type=cache,destination=/var/cache/apt \
  apt-get update \
  && apt-get dist-upgrade -y \
  && apt-get install -y \
    ccache \
    git \
    libgomp1 \
    libssl-dev \
    ninja-build

ARG CCACHE_DIR=/var/cache/ccache
ARG CFLAGS="${CFLAGS} -O3"
ARG CXXFLAGS="${CFLAGS} -O3"

ARG rebuild=''
ARG branch=master
RUN git clone --depth=1 --recurse-submodules --branch=${branch:-master} \
  https://github.com/ggml-org/llama.cpp /opt/llama
WORKDIR /opt/llama

RUN --mount=type=cache,destination=${CCACHE_DIR} \
  bash -c "source /opt/intel/oneapi/setvars.sh --force && \
    cmake -B build -G Ninja \
      -DCMAKE_BUILD_TYPE=Release \
      -DGGML_RPC=ON \
      -DGGML_SYCL=ON \
      -DGGML_SYCL_DEVICE_ARCH=${intel_arch} \
      -DCMAKE_C_COMPILER=icx \
      -DCMAKE_CXX_COMPILER=icpx \
    && cmake --build build --target rpc-server -j$(nproc) \
    && mkdir -vp /app \
    && cp -vrL build/bin/* /app/"

FROM base as app

COPY --from=build /app /app

WORKDIR /app
VOLUME /var/cache/llama
ENV ZES_ENABLE_SYSMAN=1
ENV UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
ENV GGML_RPC_DEBUG=1
ENV LLAMA_CACHE=/var/cache/llama
ENV ONEAPI_DEVICE_SELECTOR="level_zero:0"

ENTRYPOINT ["/app/rpc-server"]
CMD ["--host", "0.0.0.0", "--cache"]
EXPOSE 50052