# Tri-binary swap-stack: llama-swap + three llama-server builds.
#   /app/llama-server           TurboQuant fork (May 2026) — turbo2/3/4 KV, needed by 9B configs
#   /app-upstream/llama-server  upstream master (Jul 2026) — newest MoE/arch work
#   /app/llama-server-ik        ik_llama.cpp — -ser / -fmoe / -rtr, fast IQ-quant CPU kernels
#   /app/llama-server-ternary   PrismML fork — Q1_0/Q2_0 g128 ternary kernels (Bonsai-27B)
# config.yaml picks the binary per model (env: LD_LIBRARY_PATH for upstream).
FROM local/llama-cpp-upstream:server-cuda-sm75-mmq AS upstream
FROM local/ik-llama:server-cuda-sm75 AS ik

# ── PrismML ternary build (Q1_0_g128 hybrid-attention kernels, sm75, static) ──
# Bonsai-27B-Q1_0: 1-bit ternary, mainline/TheTom lack the g128 kernels. Built
# STATIC so it can't collide with the other forks' libs; only needs the CUDA 12.8
# runtime libs present in the final turboquant image. USE q4_0 KV + --flash-attn
# (NOT iq4_nl — CUDA FA doesn't support iq4_nl → CPU attention). Pinned 7529fdaaf.
FROM nvidia/cuda:12.8.0-devel-ubuntu22.04 AS ternary
RUN apt-get update && apt-get install -y --no-install-recommends \
        git cmake ninja-build build-essential libcurl4-openssl-dev ca-certificates \
    && rm -rf /var/lib/apt/lists/*
RUN ln -sf /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1 \
    && echo /usr/local/cuda/lib64/stubs > /etc/ld.so.conf.d/cuda-stubs.conf && ldconfig
WORKDIR /src
RUN git clone https://github.com/PrismML-Eng/llama.cpp.git . \
    && git checkout 7529fdaaf && git log --oneline -1
RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release \
        -DGGML_CUDA=ON -DGGML_NATIVE=OFF -DBUILD_SHARED_LIBS=OFF \
        -DCMAKE_CUDA_ARCHITECTURES=75 -DGGML_CUDA_F16=ON -DLLAMA_CURL=ON \
        -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
    && cmake --build build --parallel "$(nproc)" --target llama-server

FROM local/llama-cpp-turboquant:server-cuda-sm75-mmq

COPY --from=upstream /app /app-upstream
COPY --from=ik /llama-server /app-ik/llama-server
COPY --from=ik /usr/local/lib/libllama.so /usr/local/lib/libggml.so /usr/local/lib/libmtmd.so /app-ik/
COPY --from=ik /usr/local/cuda-12.4/targets/x86_64-linux/lib/libcudart.so.12 /usr/local/cuda-12.4/targets/x86_64-linux/lib/libcublas.so.12 /usr/local/cuda-12.4/targets/x86_64-linux/lib/libcublasLt.so.12 /app-ik/
COPY --from=ternary /src/build/bin/llama-server /app/llama-server-ternary
COPY llama-swap /app/llama-swap

# config.yaml is bind-mounted at runtime (see compose.yaml) so edits
# only need a container restart, not a rebuild.
ENTRYPOINT ["/app/llama-swap", "-config", "/app/config.yaml", "-listen", ":8080"]