Dockerfile

FROM archlinux:latest

ENV DEBIAN_FRONTEND=noninteractive

# passed from space environment
ARG MODEL_ID="unsloth/granite-4.0-h-tiny-GGUF"
ARG QUANT="IQ4_XS"
ARG SERVED_NAME="granite4-tiny"
ARG PARALLEL=1
ARG CTX_SIZE=8192
ARG EMBEDDING_ONLY=0
ARG RERANK_ONLY=0

# llama.cpp env configs
ENV LLAMA_ARG_HF_REPO="${MODEL_ID}:${QUANT}"
ENV LLAMA_ARG_CTX_SIZE=${CTX_SIZE}
ENV LLAMA_ARG_BATCH=512
ENV LLAMA_ARG_N_PARALLEL=${PARALLEL}
ENV LLAMA_ARG_FLASH_ATTN=on
# ENV LLAMA_ARG_CACHE_TYPE_K="q8_0"
# ENV LLAMA_ARG_CACHE_TYPE_V="q4_1"
ENV LLAMA_ARG_MLOCK=1
ENV LLAMA_ARG_N_GPU_LAYERS=0
ENV LLAMA_ARG_HOST="0.0.0.0"
ENV LLAMA_ARG_PORT=7860
ENV LLAMA_ARG_ALIAS="${SERVED_NAME}"
ENV LLAMA_ARG_EMBEDDINGS=${EMBEDDING_ONLY}
ENV LLAMA_ARG_RERANKING=${RERANK_ONLY}
ENV LLAMA_ARG_ENDPOINT_METRICS=1

RUN pacman -Syu --noconfirm --overwrite '*'
RUN pacman -S base-devel git git-lfs cmake curl emscripten nodejs python gcc-libs glibc --noconfirm --overwrite '*'

# setup emcmake
RUN source /etc/profile.d/emscripten.sh

RUN mkdir -p /app && mkdir -p /.cache
# cache dir for llama.cpp to download models
RUN chmod -R 777 /.cache

WORKDIR /app
RUN git clone --depth 1 --single-branch --branch master https://github.com/ggml-org/llama.cpp.git
# RUN git clone https://github.com/ikawrakow/ik_llama.cpp.git llama.cpp
WORKDIR /app/llama.cpp
RUN emcmake cmake -B build \
          -DGGML_LTO=ON \
          -DLLAMA_CURL=ON \
          -DLLAMA_BUILD_SERVER=ON \
          -DLLAMA_BUILD_EXAMPLES=ON \
          -DGGML_ALL_WARNINGS=OFF \
          -DGGML_ALL_WARNINGS_3RD_PARTY=OFF \
          -DGGML_WEBGPU=ON \
          -Wno-dev \
          -DCMAKE_BUILD_TYPE=Release
RUN cmake --build build --config Release --target llama-server -j $(nproc)

WORKDIR /app

EXPOSE 7860

CMD ["/app/llama.cpp/build/bin/llama-server", "--verbose-prompt", "--prio", "3"]