feat: Add support for custom llama.cpp base image and forked llama-swap repositories (#396)

* feat: Add support for custom llama.cpp base image and forked llama-swap repositories

- Introduce BASE_LLAMACPP_IMAGE env var to customize llama.cpp base image
- Introduce LS_REPO env var to customize llama-swap source
- Use GITHUB_REPOSITORY env var to automatically detect forked repos
- Update container tagging to use dynamic repo paths
- Pass build args for BASE_IMAGE and LS_REPO to Containerfile
- Enable flexible release downloads from forked repositories

* chore: quote entire curl options, appease coderabbitai

docker/build-container.sh

@@ -20,9 +20,17 @@ if [[ -z "$GITHUB_TOKEN" ]]; then
   exit 1
 fi
 
+# Set llama.cpp base image, customizable using the BASE_LLAMACPP_IMAGE environment
+# variable, this permits testing with forked llama.cpp repositories
+BASE_IMAGE=${BASE_LLAMACPP_IMAGE:-ghcr.io/ggml-org/llama.cpp}
+
+# Set llama-swap repository, automatically uses GITHUB_REPOSITORY variable
+# to enable easy container builds on forked repos
+LS_REPO=${GITHUB_REPOSITORY:-mostlygeek/llama-swap}
+
 # the most recent llama-swap tag
 # have to strip out the 'v' due to .tar.gz file naming
-LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')
+LS_VER=$(curl -s https://api.github.com/repos/${LS_REPO}/releases/latest | jq -r .tag_name | sed 's/v//')
 
 if [ "$ARCH" == "cpu" ]; then
     # cpu only containers just use the server tag
@@ -46,8 +54,8 @@ if [[ -z "$LCPP_TAG" ]]; then
 fi
 
 for CONTAINER_TYPE in non-root root; do
-  CONTAINER_TAG="ghcr.io/mostlygeek/llama-swap:v${LS_VER}-${ARCH}-${LCPP_TAG}"
-  CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:${ARCH}"
+  CONTAINER_TAG="ghcr.io/${LS_REPO}:v${LS_VER}-${ARCH}-${LCPP_TAG}"
+  CONTAINER_LATEST="ghcr.io/${LS_REPO}:${ARCH}"
   USER_UID=0
   USER_GID=0
   USER_HOME=/root
@@ -62,7 +70,8 @@ for CONTAINER_TYPE in non-root root; do
 
   echo "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
   docker build -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
-    --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} .
+    --build-arg LS_REPO=${LS_REPO} --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} \
+    --build-arg BASE_IMAGE=${BASE_IMAGE} .
   if [ "$PUSH_IMAGES" == "true" ]; then
     docker push ${CONTAINER_TAG}
     docker push ${CONTAINER_LATEST}

docker/llama-swap.Containerfile

@@ -1,8 +1,10 @@
+ARG BASE_IMAGE=ghcr.io/ggml-org/llama.cpp
 ARG BASE_TAG=server-cuda
-FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}
+FROM ${BASE_IMAGE}:${BASE_TAG}
 
 # has to be after the FROM
 ARG LS_VER=170
+ARG LS_REPO=mostlygeek/llama-swap
 
 # Set default UID/GID arguments
 ARG UID=10001
@@ -28,9 +30,9 @@ USER $UID:$GID
 
 WORKDIR /app
 RUN \
-    curl -LO https://github.com/mostlygeek/llama-swap/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_${LS_VER}_linux_amd64.tar.gz" && \
+    tar -zxf "llama-swap_${LS_VER}_linux_amd64.tar.gz" && \
+    rm "llama-swap_${LS_VER}_linux_amd64.tar.gz"
 
 COPY --chown=$UID:$GID config.example.yaml /app/config.yaml