wehub-resource-sync
133 lines
3.5 KiB
Docker
133 lines
3.5 KiB
Docker
# syntax=docker/dockerfile:1.3-labs
|
|
|
|
# The base-deps Docker image installs main libraries needed to run Ray
|
|
|
|
# The GPU options are NVIDIA CUDA developer images.
|
|
ARG BASE_IMAGE="ubuntu:22.04"
|
|
|
|
FROM ${BASE_IMAGE}
|
|
# If this arg is not "autoscaler" then no autoscaler requirements will be included
|
|
ENV TZ=America/Los_Angeles
|
|
ENV LC_ALL=C.UTF-8
|
|
ENV LANG=C.UTF-8
|
|
|
|
# TODO(ilr) $HOME seems to point to result in "" instead of "/home/ray"
|
|
# Q: Why add paths like /usr/local/nvidia/lib64 and /usr/local/nvidia/bin?
|
|
# A: The NVIDIA GPU operator version used by GKE injects these into the container
|
|
# after it's mounted to a pod.
|
|
# Issue is tracked here:
|
|
# https://github.com/GoogleCloudPlatform/compute-gpu-installation/issues/46
|
|
# More context here:
|
|
# https://github.com/NVIDIA/nvidia-container-toolkit/issues/275
|
|
# and here:
|
|
# https://gitlab.com/nvidia/container-images/cuda/-/issues/27
|
|
ENV PATH "/home/ray/anaconda3/bin:$PATH:/usr/local/nvidia/bin"
|
|
ENV LD_LIBRARY_PATH "$LD_LIBRARY_PATH:/usr/local/nvidia/lib64"
|
|
ARG DEBIAN_FRONTEND=noninteractive
|
|
ARG PYTHON_VERSION=3.10
|
|
ARG CONSTRAINTS_FILE="python/requirements_compiled_py${PYTHON_VERSION}.txt"
|
|
ARG PYTHON_DEPSET="python/deplocks/base_deps/ray_base_deps_py${PYTHON_VERSION}.lock"
|
|
|
|
ARG RAY_UID=1000
|
|
ARG RAY_GID=100
|
|
|
|
RUN <<EOF
|
|
#!/bin/bash
|
|
|
|
set -euo pipefail
|
|
|
|
apt-get update -y
|
|
apt-get upgrade -y
|
|
|
|
APT_PKGS=(
|
|
sudo
|
|
tzdata
|
|
git
|
|
libjemalloc-dev
|
|
wget
|
|
cmake
|
|
g++
|
|
zlib1g-dev
|
|
|
|
# For autoscaler
|
|
tmux
|
|
screen
|
|
rsync
|
|
netbase
|
|
openssh-client
|
|
gnupg
|
|
)
|
|
|
|
apt-get install -y "${APT_PKGS[@]}"
|
|
|
|
useradd -ms /bin/bash -d /home/ray ray --uid $RAY_UID --gid $RAY_GID
|
|
usermod -aG sudo ray
|
|
echo 'ray ALL=NOPASSWD: ALL' >> /etc/sudoers
|
|
|
|
EOF
|
|
|
|
USER $RAY_UID
|
|
ENV HOME=/home/ray
|
|
WORKDIR /home/ray
|
|
|
|
COPY --chown=ray "$CONSTRAINTS_FILE" /home/ray/requirements_compiled.txt
|
|
COPY --chown=ray "$PYTHON_DEPSET" /home/ray/python_depset.lock
|
|
|
|
SHELL ["/bin/bash", "-c"]
|
|
|
|
RUN <<EOF
|
|
#!/bin/bash
|
|
|
|
set -euo pipefail
|
|
|
|
# Determine the architecture of the host
|
|
if [[ "${HOSTTYPE}" =~ ^x86_64 ]]; then
|
|
ARCH="x86_64"
|
|
elif [[ "${HOSTTYPE}" =~ ^aarch64 ]]; then
|
|
ARCH="aarch64"
|
|
else
|
|
echo "Unsupported architecture ${HOSTTYPE}" >/dev/stderr
|
|
exit 1
|
|
fi
|
|
|
|
# Install miniforge
|
|
wget --quiet \
|
|
"https://github.com/conda-forge/miniforge/releases/download/24.11.3-0/Miniforge3-24.11.3-0-Linux-${ARCH}.sh" \
|
|
-O /tmp/miniforge.sh
|
|
|
|
/bin/bash /tmp/miniforge.sh -b -u -p $HOME/anaconda3
|
|
|
|
$HOME/anaconda3/bin/conda init
|
|
echo 'export PATH=$HOME/anaconda3/bin:$PATH' >> $HOME/.bashrc
|
|
rm /tmp/miniforge.sh
|
|
$HOME/anaconda3/bin/conda install -y libgcc-ng python=$PYTHON_VERSION
|
|
$HOME/anaconda3/bin/conda install -y -c conda-forge libffi=3.4.6
|
|
$HOME/anaconda3/bin/conda clean -y --all
|
|
|
|
# Install uv
|
|
wget -qO- https://astral.sh/uv/install.sh | sudo -E env UV_UNMANAGED_INSTALL="/usr/local/bin" sh
|
|
|
|
# Set up Conda as system Python
|
|
export PATH=$HOME/anaconda3/bin:$PATH
|
|
|
|
# Some packages are on PyPI as well as other indices, but the latter
|
|
# (unhelpfully) take precedence. We use `--index-strategy unsafe-best-match`
|
|
# to ensure that the best match is chosen from the available indices.
|
|
uv pip install --system --no-cache-dir --no-deps --index-strategy unsafe-best-match \
|
|
-r $HOME/python_depset.lock
|
|
|
|
# We install cmake temporarily to get psutil
|
|
sudo apt-get autoremove -y cmake zlib1g-dev
|
|
|
|
# We keep g++ on GPU images, because uninstalling removes CUDA Devel tooling
|
|
if [[ ! -d /usr/local/cuda ]]; then
|
|
sudo apt-get autoremove -y g++
|
|
fi
|
|
|
|
sudo rm -rf /var/lib/apt/lists/*
|
|
sudo apt-get clean
|
|
|
|
EOF
|
|
|
|
WORKDIR $HOME
|