first container code (#52)

docker/build-container.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+cd $(dirname "$0")
+
+ARCH=$1
+
+# List of allowed architectures
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda")
+
+# Check if ARCH is in the allowed list
+if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then
+  echo "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
+  exit 1
+fi
+
+# the most recent llama-swap tag
+# have to strip out the 'v' due to .tar.gz file naming
+LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')
+LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+    "https://api.github.com/users/ggerganov/packages/container/llama.cpp/versions" \
+    | jq -r --arg arch "$ARCH" '.[] | select(.metadata.container.tags[] | startswith("server-\($arch)")) | .metadata.container.tags[]' \
+    | sort -r | head -n1 | awk -F '-' '{print $3}')
+
+CONTAINER_TAG="ghcr.io/mostlygeek/llama-swap:v${LS_VER}-${ARCH}-${LCPP_TAG}"
+CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:${ARCH}"
+
+echo "Building ${CONTAINER_TAG} $LS_VER"
+docker build -f llama-swap.Containerfile --build-arg BASE_TAG=server-${ARCH}-${LCPP_TAG} --build-arg LS_VER=${LS_VER} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} .
+docker push ${CONTAINER_TAG}
+docker push ${CONTAINER_LATEST}

docker/llama-swap-cuda.Containerfile

@@ -0,0 +1,15 @@
+ARG BASE_TAG=server-cuda
+FROM ghcr.io/ggerganov/llama.cpp:${BASE_TAG}
+
+# has to be after the FROM
+ARG LS_VER=89
+
+WORKDIR /app
+
+RUN \
+    curl -LO https://github.com/mostlygeek/llama-swap/releases/download/v"${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
+
+
+ENTRYPOINT [ "/app/llama-swap", "--config", "/config.yaml" ]