FROM nvidia/cuda:12.2.0-devel-ubuntu20.04 AS build

ENV DEBIAN_FRONTEND=noninteractive

# inlude kitware apt repo to allow us to grab latest cmake

RUN apt-get update && apt-get install ca-certificates gpg wget

RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null

RUN echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ focal main' | tee /etc/apt/sources.list.d/kitware.list >/dev/null

RUN apt-get update && apt-get install -y build-essential cmake libboost-dev libboost-thread-dev

ADD ./ /turbopilot

RUN mkdir /turbopilot/build

WORKDIR /turbopilot/build

RUN cmake -DGGML_CUBLAS=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc ..

RUN make turbopilot

FROM nvidia/cuda:12.2.0-runtime-ubuntu20.04 AS runtime

WORKDIR /app

COPY --from=build /turbopilot/build/bin/turbopilot /app/turbopilot

ENV THREADS=4

ENV MODEL="/models/codegen-2B-multi-ggml-4bit-quant.bin"

ENV BATCHSIZE=64

COPY ./run.sh /app/

EXPOSE 18080

CMD /app/run.sh