mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-11 18:27:32 -04:00
ci: layered Python base images for cross-matrix dedup
The 234-entry backend matrix runs the same apt-update + GPU SDK install + Python toolchain bootstrap into N independent registry-cache tags. Factor that shared work out into a tier-1+2 base image (lang × accel × ubuntu × cuda) built once per workflow run, then consumed by every backend that matches its tuple via BASE_IMAGE_PREBUILT. The matrix data moves to .github/backend-matrix.yaml so backend.yml can switch to fromJSON without duplicating the matrix. scripts/changed-backends.js reads the data file, derives the deduplicated bases-matrix, annotates each Python entry with the right base-image-prebuilt ref, and runs a collision check that fails loudly if a future matrix change makes two consumers want incompatible bases under the same tag-stem. PR builds tag with -pr<N> so end-to-end validation lives within one PR; master builds tag without the suffix. The base-images registry cache parallels the existing per-matrix-entry caches. Adding a new (accel, cuda) flavour is a backend-matrix.yaml edit; adding a new language tier is a Dockerfile.<lang> recipe + a slim of the consumer Dockerfile (script auto-detects via .docker/bases/). 10 distinct bases derive from the current 234 entries, replacing the inline bootstrap that previously ran into ~10 separate cache tags. Assisted-by: Claude:opus-4-7-1m [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com>
This commit is contained in:
Richard Palethorpe
@@ -1,202 +1,26 @@
|
||||
ARG BASE_IMAGE=ubuntu:24.04
|
||||
ARG APT_MIRROR=""
|
||||
ARG APT_PORTS_MIRROR=""
|
||||
# Builds a single Python backend on top of the shared
|
||||
# .docker/bases/Dockerfile.python base. The base bakes in apt-update + GPU
|
||||
# SDK install + python toolchain (uv, pip, rustup, grpcio-tools), so this
|
||||
# stage only carries the per-backend source COPY + `make`.
|
||||
#
|
||||
# CI orchestration (.github/workflows/backend.yml + backend_pr.yml) builds
|
||||
# the right base flavour automatically via scripts/derive-build-matrix.js
|
||||
# and passes BASE_IMAGE_PREBUILT here. For local builds, run:
|
||||
# make backend-image-base BUILD_TYPE=<...> # build the base
|
||||
# make backend-image BACKEND=<...> BUILD_TYPE=<...>
|
||||
# See .agents/ci-caching.md.
|
||||
|
||||
ARG BASE_IMAGE_PREBUILT
|
||||
|
||||
FROM ${BASE_IMAGE_PREBUILT} AS builder
|
||||
|
||||
FROM ${BASE_IMAGE} AS builder
|
||||
ARG BACKEND=rerankers
|
||||
ARG BUILD_TYPE
|
||||
ENV BUILD_TYPE=${BUILD_TYPE}
|
||||
ARG CUDA_MAJOR_VERSION
|
||||
ARG CUDA_MINOR_VERSION
|
||||
ARG SKIP_DRIVERS=false
|
||||
ENV CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION}
|
||||
ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION}
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ARG TARGETARCH
|
||||
ARG TARGETVARIANT
|
||||
ARG UBUNTU_VERSION=2404
|
||||
ARG APT_MIRROR
|
||||
ARG APT_PORTS_MIRROR
|
||||
|
||||
RUN --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mirror \
|
||||
APT_MIRROR="${APT_MIRROR}" APT_PORTS_MIRROR="${APT_PORTS_MIRROR}" sh /usr/local/sbin/apt-mirror && \
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
build-essential \
|
||||
ccache \
|
||||
ca-certificates \
|
||||
espeak-ng \
|
||||
curl \
|
||||
libssl-dev \
|
||||
git wget \
|
||||
git-lfs \
|
||||
unzip clang \
|
||||
upx-ucl \
|
||||
curl python3-pip \
|
||||
python-is-python3 \
|
||||
python3-dev llvm \
|
||||
libnuma1 libgomp1 \
|
||||
python3-venv make cmake && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN <<EOT bash
|
||||
if [ "${UBUNTU_VERSION}" = "2404" ]; then
|
||||
pip install --break-system-packages --user --upgrade pip
|
||||
else
|
||||
pip install --upgrade pip
|
||||
fi
|
||||
EOT
|
||||
|
||||
|
||||
# Cuda
|
||||
ENV PATH=/usr/local/cuda/bin:${PATH}
|
||||
|
||||
# HipBLAS requirements
|
||||
ENV PATH=/opt/rocm/bin:${PATH}
|
||||
|
||||
# Vulkan requirements
|
||||
RUN <<EOT bash
|
||||
if [ "${BUILD_TYPE}" = "vulkan" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
software-properties-common pciutils wget gpg-agent && \
|
||||
apt-get install -y libglm-dev cmake libxcb-dri3-0 libxcb-present0 libpciaccess0 \
|
||||
libpng-dev libxcb-keysyms1-dev libxcb-dri3-dev libx11-dev g++ gcc \
|
||||
libwayland-dev libxrandr-dev libxcb-randr0-dev libxcb-ewmh-dev \
|
||||
git python-is-python3 bison libx11-xcb-dev liblz4-dev libzstd-dev \
|
||||
ocaml-core ninja-build pkg-config libxml2-dev wayland-protocols python3-jsonschema \
|
||||
clang-format qtbase5-dev qt6-base-dev libxcb-glx0-dev sudo xz-utils
|
||||
if [ "amd64" = "$TARGETARCH" ]; then
|
||||
wget "https://sdk.lunarg.com/sdk/download/1.4.335.0/linux/vulkansdk-linux-x86_64-1.4.335.0.tar.xz" && \
|
||||
tar -xf vulkansdk-linux-x86_64-1.4.335.0.tar.xz && \
|
||||
rm vulkansdk-linux-x86_64-1.4.335.0.tar.xz && \
|
||||
mkdir -p /opt/vulkan-sdk && \
|
||||
mv 1.4.335.0 /opt/vulkan-sdk/ && \
|
||||
cd /opt/vulkan-sdk/1.4.335.0 && \
|
||||
./vulkansdk --no-deps --maxjobs \
|
||||
vulkan-loader \
|
||||
vulkan-validationlayers \
|
||||
vulkan-extensionlayer \
|
||||
vulkan-tools \
|
||||
shaderc && \
|
||||
cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/bin/* /usr/bin/ && \
|
||||
cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/lib/* /usr/lib/x86_64-linux-gnu/ && \
|
||||
cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/include/* /usr/include/ && \
|
||||
cp -rfv /opt/vulkan-sdk/1.4.335.0/x86_64/share/* /usr/share/ && \
|
||||
rm -rf /opt/vulkan-sdk
|
||||
fi
|
||||
if [ "arm64" = "$TARGETARCH" ]; then
|
||||
mkdir vulkan && cd vulkan && \
|
||||
curl -L -o vulkan-sdk.tar.xz https://github.com/mudler/vulkan-sdk-arm/releases/download/1.4.335.0/vulkansdk-ubuntu-24.04-arm-1.4.335.0.tar.xz && \
|
||||
tar -xvf vulkan-sdk.tar.xz && \
|
||||
rm vulkan-sdk.tar.xz && \
|
||||
cd 1.4.335.0 && \
|
||||
cp -rfv aarch64/bin/* /usr/bin/ && \
|
||||
cp -rfv aarch64/lib/* /usr/lib/aarch64-linux-gnu/ && \
|
||||
cp -rfv aarch64/include/* /usr/include/ && \
|
||||
cp -rfv aarch64/share/* /usr/share/ && \
|
||||
cd ../.. && \
|
||||
rm -rf vulkan
|
||||
fi
|
||||
ldconfig && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
fi
|
||||
EOT
|
||||
|
||||
# CuBLAS requirements
|
||||
RUN <<EOT bash
|
||||
if ( [ "${BUILD_TYPE}" = "cublas" ] || [ "${BUILD_TYPE}" = "l4t" ] ) && [ "${SKIP_DRIVERS}" = "false" ]; then
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
software-properties-common pciutils
|
||||
if [ "amd64" = "$TARGETARCH" ]; then
|
||||
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/x86_64/cuda-keyring_1.1-1_all.deb
|
||||
fi
|
||||
if [ "arm64" = "$TARGETARCH" ]; then
|
||||
if [ "${CUDA_MAJOR_VERSION}" = "13" ]; then
|
||||
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/sbsa/cuda-keyring_1.1-1_all.deb
|
||||
else
|
||||
curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${UBUNTU_VERSION}/arm64/cuda-keyring_1.1-1_all.deb
|
||||
fi
|
||||
fi
|
||||
dpkg -i cuda-keyring_1.1-1_all.deb && \
|
||||
rm -f cuda-keyring_1.1-1_all.deb && \
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
||||
libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
||||
libcurand-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
||||
libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
||||
libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
|
||||
libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
|
||||
if [ "${CUDA_MAJOR_VERSION}" = "13" ] && [ "arm64" = "$TARGETARCH" ]; then
|
||||
apt-get install -y --no-install-recommends \
|
||||
libcufile-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcudnn9-cuda-${CUDA_MAJOR_VERSION} cuda-cupti-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libnvjitlink-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
|
||||
fi
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
fi
|
||||
EOT
|
||||
|
||||
|
||||
# https://github.com/NVIDIA/Isaac-GR00T/issues/343
|
||||
RUN <<EOT bash
|
||||
if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "arm64" ]; then
|
||||
wget https://developer.download.nvidia.com/compute/cudss/0.6.0/local_installers/cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0_0.6.0-1_arm64.deb && \
|
||||
dpkg -i cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0_0.6.0-1_arm64.deb && \
|
||||
cp /var/cudss-local-tegra-repo-ubuntu${UBUNTU_VERSION}-0.6.0/cudss-*-keyring.gpg /usr/share/keyrings/ && \
|
||||
apt-get update && apt-get -y install cudss cudss-cuda-${CUDA_MAJOR_VERSION} && \
|
||||
wget https://developer.download.nvidia.com/compute/nvpl/25.5/local_installers/nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5_1.0-1_arm64.deb && \
|
||||
dpkg -i nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5_1.0-1_arm64.deb && \
|
||||
cp /var/nvpl-local-repo-ubuntu${UBUNTU_VERSION}-25.5/nvpl-*-keyring.gpg /usr/share/keyrings/ && \
|
||||
apt-get update && apt-get install -y nvpl
|
||||
fi
|
||||
EOT
|
||||
|
||||
# If we are building with clblas support, we need the libraries for the builds
|
||||
RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
libclblast-dev && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/* \
|
||||
; fi
|
||||
|
||||
RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
hipblas-dev \
|
||||
hipblaslt-dev \
|
||||
rocblas-dev && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/* && \
|
||||
# I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able
|
||||
# to locate the libraries. We run ldconfig ourselves to work around this packaging deficiency
|
||||
ldconfig \
|
||||
; fi
|
||||
|
||||
RUN if [ "${BUILD_TYPE}" = "hipblas" ]; then \
|
||||
ln -s /opt/rocm-**/lib/llvm/lib/libomp.so /usr/lib/libomp.so \
|
||||
; fi
|
||||
|
||||
# Install uv as a system package
|
||||
RUN curl -LsSf https://astral.sh/uv/install.sh | UV_INSTALL_DIR=/usr/bin sh
|
||||
ENV PATH="/root/.cargo/bin:${PATH}"
|
||||
# Increase timeout for uv installs behind slow networks
|
||||
ENV UV_HTTP_TIMEOUT=180
|
||||
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
|
||||
|
||||
# Install grpcio-tools (the version in 22.04 is too old)
|
||||
RUN <<EOT bash
|
||||
if [ "${UBUNTU_VERSION}" = "2404" ]; then
|
||||
pip install --break-system-packages --user grpcio-tools==1.71.0 grpcio==1.71.0
|
||||
else
|
||||
pip install grpcio-tools==1.71.0 grpcio==1.71.0
|
||||
fi
|
||||
EOT
|
||||
|
||||
|
||||
COPY backend/python/${BACKEND} /${BACKEND}
|
||||
COPY backend/backend.proto /${BACKEND}/backend.proto
|
||||
|
||||
Reference in New Issue
Block a user