# Builds the llama-cpp backend on top of the shared
# .docker/bases/Dockerfile.cpp base. The base bakes in apt + GPU SDK +
# protoc + cmake + GRPC, so this stage only carries the COPY + `make`
# invocations and the final scratch-stage package.
#
# CI orchestration (.github/workflows/backend.yml + backend_pr.yml) passes
# BASE_IMAGE_PREBUILT. See .agents/ci-caching.md.

ARG BASE_IMAGE_PREBUILT

FROM ${BASE_IMAGE_PREBUILT} AS builder

# We can target specific CUDA ARCHITECTURES like --build-arg CUDA_DOCKER_ARCH='75;86;89;120'
ARG CUDA_DOCKER_ARCH
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
ARG CMAKE_ARGS
ENV CMAKE_ARGS=${CMAKE_ARGS}
ARG AMDGPU_TARGETS
ENV AMDGPU_TARGETS=${AMDGPU_TARGETS}
ARG BACKEND=llama-cpp
ARG BUILD_TYPE
ENV BUILD_TYPE=${BUILD_TYPE}
ARG CUDA_MAJOR_VERSION
ARG CUDA_MINOR_VERSION
ENV CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION}
ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION}
ARG TARGETARCH
ARG TARGETVARIANT

COPY . /LocalAI

RUN <<'EOT' bash
set -euxo pipefail

if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
  CUDA_ARCH_ESC="${CUDA_DOCKER_ARCH//;/\\;}"
  export CMAKE_ARGS="${CMAKE_ARGS:-} -DCMAKE_CUDA_ARCHITECTURES=${CUDA_ARCH_ESC}"
  echo "CMAKE_ARGS(env) = ${CMAKE_ARGS}"
  rm -rf /LocalAI/backend/cpp/llama-cpp-*-build
fi

if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
  cd /LocalAI/backend/cpp/llama-cpp
  make llama-cpp-fallback
  make llama-cpp-grpc
  make llama-cpp-rpc-server
else
  cd /LocalAI/backend/cpp/llama-cpp
  make llama-cpp-avx
  make llama-cpp-avx2
  make llama-cpp-avx512
  make llama-cpp-fallback
  make llama-cpp-grpc
  make llama-cpp-rpc-server
fi
EOT


# Copy libraries using a script to handle architecture differences
RUN make -BC /LocalAI/backend/cpp/llama-cpp package


FROM scratch


# Copy all available binaries (the build process only creates the appropriate ones for the target architecture)
COPY --from=builder /LocalAI/backend/cpp/llama-cpp/package/. ./