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.
This commit is contained in:
rhtenhove
2026-05-12 06:03:48 +02:00
committed by GitHub
parent 085b54bc88
commit 174e8562aa
3 changed files with 80 additions and 14 deletions
+6 -3
View File
@@ -3,6 +3,9 @@ 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
@@ -34,9 +37,9 @@ WORKDIR /app
ENV PATH="/app:${PATH}"
RUN \
curl -LO "https://github.com/${LS_REPO}/releases/download/v${LS_VER}/llama-swap_${LS_VER}_linux_amd64.tar.gz" && \
tar -zxf "llama-swap_${LS_VER}_linux_amd64.tar.gz" && \
rm "llama-swap_${LS_VER}_linux_amd64.tar.gz"
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