Files
llama-swap/docker/llama-swap.Containerfile
T
rhtenhove 174e8562aa Multi arch cpu (#746)
Encountered a similar problem as in
https://github.com/mostlygeek/llama-swap/issues/709 but in my case I
only needed the :cpu version.

So decided to add the github action to build arm64 combined with the
amd64 version on the same :cpu tag. Already tested it from this fork:
ghcr.io/rhtenhove/llama-swap:cpu and it works perfectly fine.

Adding GPU support is a whole other beast, needing quite a bit more work
and isn't something I can test.
2026-05-11 21:03:48 -07:00

48 lines
1.3 KiB
Docker

ARG BASE_IMAGE=ghcr.io/ggml-org/llama.cpp
ARG BASE_TAG=server-cuda
FROM ${BASE_IMAGE}:${BASE_TAG}
# has to be after the FROM
# TARGETARCH is auto-set by `docker buildx build --platform …` (amd64/arm64);
# falls back to amd64 when an older `docker build` runs without buildx.
ARG TARGETARCH=amd64
ARG LS_VER=170
ARG LS_REPO=mostlygeek/llama-swap
# Set default UID/GID arguments
ARG UID=10001
ARG GID=10001
ARG USER_HOME=/app
# Add user/group
ENV HOME=$USER_HOME
RUN if [ $UID -ne 0 ]; then \
if [ $GID -ne 0 ]; then \
groupadd --system --gid $GID app; \
fi; \
useradd --system --uid $UID --gid $GID \
--home $USER_HOME app; \
fi
# Handle paths
RUN mkdir --parents $HOME /app
RUN chown --recursive $UID:$GID $HOME /app
# Switch user
USER $UID:$GID
WORKDIR /app
# Add /app to PATH
ENV PATH="/app:${PATH}"
RUN \
curl -LO "https://github.com/${LS_REPO}/releases/download/v${LS_VER}/llama-swap_${LS_VER}_linux_${TARGETARCH}.tar.gz" && \
tar -zxf "llama-swap_${LS_VER}_linux_${TARGETARCH}.tar.gz" && \
rm "llama-swap_${LS_VER}_linux_${TARGETARCH}.tar.gz"
COPY --chown=$UID:$GID config.example.yaml /app/config.yaml
HEALTHCHECK CMD curl -f http://localhost:8080/ || exit 1
ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]