chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,14 @@
|
||||
Overview of how the ray images are built:
|
||||
|
||||
Images without a "-cpu" or "-gpu" tag are built on ``ubuntu:22.04``. They are just an alias for **-cpu** (e.g. ``ray:latest`` is the same as ``ray:latest-cpu``).
|
||||
|
||||
```
|
||||
ubuntu:22.04
|
||||
└── base-deps:cpu
|
||||
└── ray:cpu
|
||||
|
||||
nvidia/cuda
|
||||
└── base-deps:cudaXXX
|
||||
└── ray:cudaXXX
|
||||
└── ray-llm:cudaXXX
|
||||
```
|
||||
@@ -0,0 +1 @@
|
||||
# DEPRECATED -- Please use [`rayproject/ray-ml`](https://hub.docker.com/repository/docker/rayproject/ray-ml)
|
||||
@@ -0,0 +1,132 @@
|
||||
# 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
|
||||
@@ -0,0 +1,42 @@
|
||||
## About
|
||||
This is an internal image, the [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) or [`rayproject/ray-ml`](https://hub.docker.com/repository/docker/rayproject/ray-ml) should be used!
|
||||
|
||||
|
||||
This image has the system-level dependencies for `Ray` and the `Ray Autoscaler`. The `ray-deps` image is built on top of this. This image is built periodically or when dependencies are added. [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/base-deps/Dockerfile)
|
||||
|
||||
## Tags
|
||||
|
||||
Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}][-{Architecture}]`. `Ray version` tag can be one of the following:
|
||||
|
||||
| Ray version tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `latest` | The most recent Ray release. |
|
||||
| `x.y.z` | A specific Ray release, e.g. 2.9.3 |
|
||||
| `nightly` | The most recent Ray development build (a recent commit from GitHub `master`) |
|
||||
|
||||
The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py39`, `py310` and `py311`. If unspecified, the tag points to an image using `Python 3.9`.
|
||||
|
||||
The optional `Platform` tag specifies the platform where the image is intended for:
|
||||
|
||||
| Platform tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `-cpu` | These are based off of an Ubuntu image. |
|
||||
| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the NVIDIA Docker Runtime. |
|
||||
| `-gpu` | Aliases to a specific `-cuXX` tagged image. |
|
||||
| no tag | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
|
||||
|
||||
The optional `Architecture` tag can be used to specify images for different CPU architectures.
|
||||
Currently, we support the `x86_64` (`amd64`) and `aarch64` (`arm64`) architectures.
|
||||
|
||||
Please note that suffixes are only used to specify `aarch64` images. No suffix means
|
||||
`x86_64`/`amd64`-compatible images.
|
||||
|
||||
| Platform tag | Description |
|
||||
|--------------|-------------------------|
|
||||
| `-aarch64` | arm64-compatible images |
|
||||
| no tag | Defaults to `amd64` |
|
||||
|
||||
|
||||
----
|
||||
|
||||
See [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) for Ray and all of its dependencies.
|
||||
@@ -0,0 +1,12 @@
|
||||
name: "ray-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX"
|
||||
froms: ["ubuntu:22.04"]
|
||||
dockerfile: docker/base-deps/Dockerfile
|
||||
srcs:
|
||||
- python/requirements_compiled.txt
|
||||
- python/requirements_compiled_py$PYTHON_VERSION.txt
|
||||
- python/deplocks/base_deps/ray_base_deps_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- PYTHON_VERSION
|
||||
- BASE_IMAGE=ubuntu:22.04
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX
|
||||
@@ -0,0 +1,12 @@
|
||||
name: "ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX"
|
||||
froms: ["nvidia/cuda:$CUDA_VERSION-devel-ubuntu22.04"]
|
||||
dockerfile: docker/base-deps/Dockerfile
|
||||
srcs:
|
||||
- python/requirements_compiled.txt
|
||||
- python/requirements_compiled_py$PYTHON_VERSION.txt
|
||||
- python/deplocks/base_deps/ray_base_deps_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- PYTHON_VERSION
|
||||
- BASE_IMAGE=nvidia/cuda:$CUDA_VERSION-devel-ubuntu22.04
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX
|
||||
@@ -0,0 +1,14 @@
|
||||
setuptools==80.9.0
|
||||
flatbuffers
|
||||
cython
|
||||
numpy # Necessary for Dataset to work properly.
|
||||
psutil
|
||||
# For the ease to submit jobs on various cloud providers.
|
||||
smart_open[s3,gcs,azure,http]
|
||||
six
|
||||
boto3
|
||||
pyopenssl
|
||||
cryptography
|
||||
google-api-python-client
|
||||
google-oauth
|
||||
adlfs[abfs]
|
||||
@@ -0,0 +1,18 @@
|
||||
# Pin to satisfy both cupy (needs <2.3) and JAX (needs >2.0)
|
||||
numpy>=2.0
|
||||
|
||||
# Minimum version for tpu7x compatibility
|
||||
jax[tpu]>=0.8.2; python_version >= "3.11"
|
||||
jax[tpu]; python_version < "3.11"
|
||||
|
||||
# Standard JAX ecosystem dependencies
|
||||
flax
|
||||
optax
|
||||
orbax-checkpoint
|
||||
ml-collections
|
||||
|
||||
# TPU profiling & telemetry
|
||||
cloud-tpu-diagnostics
|
||||
tensorboard-plugin-profile
|
||||
ml-goodput-measurement
|
||||
tpu-info
|
||||
@@ -0,0 +1,13 @@
|
||||
name: "ray-py$PYTHON_VERSION-tpu-base$ARCH_SUFFIX"
|
||||
froms: ["ubuntu:22.04"]
|
||||
dockerfile: docker/base-deps/Dockerfile
|
||||
srcs:
|
||||
- python/requirements_compiled.txt
|
||||
- python/requirements_compiled_py$PYTHON_VERSION.txt
|
||||
- python/deplocks/base_deps/ray_base_deps_tpu_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- PYTHON_VERSION
|
||||
- BASE_IMAGE=ubuntu:22.04
|
||||
- PYTHON_DEPSET=python/deplocks/base_deps/ray_base_deps_tpu_py$PYTHON_VERSION.lock
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-py$PYTHON_VERSION-tpu-base$ARCH_SUFFIX
|
||||
@@ -0,0 +1,11 @@
|
||||
name: "$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra-testdeps"
|
||||
froms: ["cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra"]
|
||||
dockerfile: release/ray_release/byod/byod.Dockerfile
|
||||
srcs:
|
||||
- python/deplocks/base_extra_testdeps/$IMAGE_TYPE-base_extra_testdeps_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- BASE_IMAGE=cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra
|
||||
- PYTHON_VERSION
|
||||
- IMAGE_TYPE
|
||||
tags:
|
||||
- cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra-testdeps
|
||||
@@ -0,0 +1,11 @@
|
||||
name: "$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra-testdeps"
|
||||
froms: ["cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra"]
|
||||
dockerfile: release/ray_release/byod/byod.Dockerfile
|
||||
srcs:
|
||||
- python/deplocks/base_extra_testdeps/$IMAGE_TYPE-base_extra_testdeps_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- BASE_IMAGE=cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra
|
||||
- PYTHON_VERSION
|
||||
- IMAGE_TYPE
|
||||
tags:
|
||||
- cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra-testdeps
|
||||
@@ -0,0 +1,193 @@
|
||||
# syntax=docker/dockerfile:1.3-labs
|
||||
|
||||
ARG BASE_IMAGE="rayproject/ray:latest"
|
||||
|
||||
FROM "$BASE_IMAGE"
|
||||
|
||||
ENV TERM=xterm
|
||||
|
||||
ARG SSH_PORT=5020
|
||||
|
||||
ARG PYTHON_VERSION=3.10
|
||||
ARG PYTHON_DEPSET="python/deplocks/base_extra/ray_base_extra_py${PYTHON_VERSION}.lock"
|
||||
|
||||
COPY "$PYTHON_DEPSET" /home/ray/python_depset.lock
|
||||
|
||||
RUN <<EOF
|
||||
#!/bin/bash
|
||||
|
||||
set -exuo pipefail
|
||||
|
||||
if [[ "$HOSTTYPE" =~ ^x86_64 ]]; then
|
||||
ARCH="x86_64"
|
||||
elif [[ "$HOSTTYPE" =~ ^aarch64 ]]; then
|
||||
ARCH="aarch64"
|
||||
else
|
||||
echo "Unsupported architecture $MACHTYPE" >/dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Create boto config; makes gsutil happy.
|
||||
echo "[GoogleCompute]" > "${HOME}/.boto"
|
||||
echo "service_account = default" >> "${HOME}/.boto"
|
||||
chmod 600 "${HOME}/.boto"
|
||||
|
||||
if [[ "$ARCH" == "x86_64" ]]; then
|
||||
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
|
||||
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
|
||||
else
|
||||
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/arm64/7fa2af80.pub
|
||||
# Nvidia does not have machine-learning repo for arm64
|
||||
fi
|
||||
|
||||
echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" \
|
||||
| sudo tee -a /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
wget -O - https://packages.cloud.google.com/apt/doc/apt-key.gpg \
|
||||
| sudo apt-key --keyring /usr/share/keyrings/cloud.google.gpg add -
|
||||
|
||||
# Add gdb since ray dashboard uses `memray attach`, which requires gdb.
|
||||
|
||||
APT_PKGS=(
|
||||
google-cloud-sdk
|
||||
supervisor
|
||||
vim
|
||||
zsh
|
||||
nfs-common
|
||||
zip
|
||||
unzip
|
||||
build-essential
|
||||
ssh
|
||||
curl
|
||||
gdb
|
||||
)
|
||||
|
||||
sudo apt-get update -y
|
||||
sudo apt-get install -y "${APT_PKGS[@]}"
|
||||
sudo apt-get autoclean
|
||||
|
||||
# Install azcopy
|
||||
AZCOPY_VERSION="10.30.0"
|
||||
AZCOPY_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${AZCOPY_TMP}"
|
||||
if [[ "$ARCH" == "x86_64" ]]; then
|
||||
curl -sSfL "https://github.com/Azure/azure-storage-azcopy/releases/download/v${AZCOPY_VERSION}/azcopy_linux_amd64_${AZCOPY_VERSION}.tar.gz" \
|
||||
-o- | tar -xz "azcopy_linux_amd64_${AZCOPY_VERSION}/azcopy"
|
||||
sudo mv "azcopy_linux_amd64_${AZCOPY_VERSION}/azcopy" /usr/local/bin/azcopy
|
||||
else
|
||||
curl -sSfL "https://github.com/Azure/azure-storage-azcopy/releases/download/v${AZCOPY_VERSION}/azcopy_linux_arm64_${AZCOPY_VERSION}.tar.gz" \
|
||||
-o- | tar -xz "azcopy_linux_arm64_${AZCOPY_VERSION}/azcopy"
|
||||
sudo mv "azcopy_linux_arm64_${AZCOPY_VERSION}/azcopy" /usr/local/bin/azcopy
|
||||
fi
|
||||
)
|
||||
rm -rf "${AZCOPY_TMP}"
|
||||
|
||||
# Install dynolog, only on x86_64 machines.
|
||||
if [[ "$ARCH" == "x86_64" ]]; then
|
||||
DYNOLOG_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${DYNOLOG_TMP}"
|
||||
curl -sSL https://github.com/facebookincubator/dynolog/releases/download/v0.3.2/dynolog_0.3.2-0-amd64.deb -o dynolog_0.3.2-0-amd64.deb
|
||||
sudo dpkg -i dynolog_0.3.2-0-amd64.deb
|
||||
)
|
||||
rm -rf "${DYNOLOG_TMP}"
|
||||
fi
|
||||
|
||||
uv pip install --system --no-cache-dir --no-deps --index-strategy unsafe-best-match \
|
||||
-r $HOME/python_depset.lock
|
||||
|
||||
# Install awscli v2
|
||||
AWSCLI_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${AWSCLI_TMP}"
|
||||
curl -sfL "https://awscli.amazonaws.com/awscli-exe-linux-${ARCH}.zip" -o "awscliv2.zip"
|
||||
unzip -q awscliv2.zip
|
||||
sudo ./aws/install
|
||||
)
|
||||
rm -rf "${AWSCLI_TMP}"
|
||||
|
||||
# Cleanup unused packages and caches.
|
||||
$HOME/anaconda3/bin/conda clean -y -all
|
||||
|
||||
# Work around for https://bugs.launchpad.net/ubuntu/+source/openssh/+bug/45234
|
||||
sudo mkdir -p /var/run/sshd
|
||||
# Configure ssh port
|
||||
echo Port $SSH_PORT | sudo tee -a /etc/ssh/sshd_config
|
||||
|
||||
if [[ ! -d /usr/local/cuda ]]; then
|
||||
EFA_VERSION="1.42.0"
|
||||
GDRCOPY_VERSION=""
|
||||
AWS_OFI_NCCL_VERSION=""
|
||||
elif [[ -d "/usr/local/cuda-11" ]]; then
|
||||
EFA_VERSION="1.28.0"
|
||||
GDRCOPY_VERSION="2.4"
|
||||
AWS_OFI_NCCL_VERSION="1.7.3-aws"
|
||||
elif [[ -d "/usr/local/cuda-12" ]]; then
|
||||
EFA_VERSION="1.42.0"
|
||||
GDRCOPY_VERSION="2.5"
|
||||
AWS_OFI_NCCL_VERSION="1.15.0"
|
||||
elif [[ -d "/usr/local/cuda-13" ]]; then
|
||||
EFA_VERSION="1.42.0"
|
||||
GDRCOPY_VERSION="2.5.1"
|
||||
AWS_OFI_NCCL_VERSION="1.18.0"
|
||||
else
|
||||
echo "Unsupported CUDA major version"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Install EFA
|
||||
wget -q "https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_VERSION}.tar.gz" -O "/tmp/aws-efa-installer-${EFA_VERSION}.tar.gz"
|
||||
wget -q "https://efa-installer.amazonaws.com/aws-efa-installer.key" -O /tmp/aws-efa-installer.key && gpg --import /tmp/aws-efa-installer.key
|
||||
gpg --fingerprint </tmp/aws-efa-installer.key
|
||||
wget -q "https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_VERSION}.tar.gz.sig" -O "/tmp/aws-efa-installer-${EFA_VERSION}.tar.gz.sig"
|
||||
gpg --verify "/tmp/aws-efa-installer-${EFA_VERSION}.tar.gz.sig"
|
||||
tar -xzf "/tmp/aws-efa-installer-${EFA_VERSION}.tar.gz" -C /tmp
|
||||
(cd /tmp/aws-efa-installer; sudo bash efa_installer.sh --yes --skip-kmod)
|
||||
rm -rf "/tmp/aws-efa-installer-${EFA_VERSION}.tar.gz" /tmp/aws-efa-installer.key /tmp/aws-efa-installer
|
||||
|
||||
# Install GDRCopy
|
||||
if [[ "${GDRCOPY_VERSION}" != "" ]]; then
|
||||
echo "Installing gdrcopy for GPU images"
|
||||
sudo apt-get -y install build-essential devscripts debhelper check libsubunit-dev fakeroot pkg-config dkms
|
||||
wget -q "https://github.com/NVIDIA/gdrcopy/archive/refs/tags/v${GDRCOPY_VERSION}.tar.gz" -O "/tmp/v${GDRCOPY_VERSION}.tar.gz"
|
||||
tar -xzf "/tmp/v${GDRCOPY_VERSION}.tar.gz" -C /tmp
|
||||
(
|
||||
cd "/tmp/gdrcopy-${GDRCOPY_VERSION}"
|
||||
sudo make -j`nproc` lib_install
|
||||
)
|
||||
rm -rf "/tmp/gdrcopy-${GDRCOPY_VERSION}"
|
||||
else
|
||||
echo "Skip installing gdrcopy"
|
||||
fi
|
||||
|
||||
# Install AWS OFI NCCL
|
||||
if [[ "${AWS_OFI_NCCL_VERSION}" != "" ]]; then
|
||||
echo "Installing aws-ofi-nccl"
|
||||
sudo apt-get install -y autoconf libhwloc-dev
|
||||
(
|
||||
cd /tmp
|
||||
git clone --depth=1 "https://github.com/aws/aws-ofi-nccl.git" -b "v${AWS_OFI_NCCL_VERSION}"
|
||||
)
|
||||
(
|
||||
cd /tmp/aws-ofi-nccl
|
||||
./autogen.sh
|
||||
./configure --with-libfabric=/opt/amazon/efa \
|
||||
--with-mpi=/opt/amazon/openmpi \
|
||||
--with-cuda=/usr/local/cuda \
|
||||
--with-nccl=/usr/local --prefix=/usr/local
|
||||
make -j`nproc`
|
||||
sudo make install
|
||||
)
|
||||
rm -rf /tmp/aws-ofi-nccl
|
||||
else
|
||||
echo "Skip installing aws-ofi-nccl"
|
||||
fi
|
||||
|
||||
# Remove apt sources so that it won't run into apt update issues when running
|
||||
# the image.
|
||||
sudo rm -rf /etc/apt/sources.list.d/*
|
||||
sudo rm -rf /var/lib/apt/lists/*
|
||||
|
||||
EOF
|
||||
|
||||
RUN mkdir -p /tmp/supervisord
|
||||
@@ -0,0 +1,10 @@
|
||||
name: "$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra$ARCH_SUFFIX"
|
||||
froms: ["cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX"]
|
||||
dockerfile: docker/base-extra/Dockerfile
|
||||
srcs:
|
||||
- python/deplocks/base_extra/ray_base_extra_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- BASE_IMAGE=cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX
|
||||
- PYTHON_VERSION
|
||||
tags:
|
||||
- cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cpu-base-extra$ARCH_SUFFIX
|
||||
@@ -0,0 +1,10 @@
|
||||
name: "$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra$ARCH_SUFFIX"
|
||||
froms: ["cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX"]
|
||||
dockerfile: docker/base-extra/Dockerfile
|
||||
srcs:
|
||||
- python/deplocks/base_extra/ray_base_extra_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- BASE_IMAGE=cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX
|
||||
- PYTHON_VERSION
|
||||
tags:
|
||||
- cr.ray.io/rayproject/$IMAGE_TYPE-py$PYTHON_VERSION-cu$CUDA_VERSION-base-extra$ARCH_SUFFIX
|
||||
@@ -0,0 +1,11 @@
|
||||
azure-identity
|
||||
datasketches
|
||||
jupyterlab
|
||||
ipywidgets
|
||||
grpcio
|
||||
grpcio-tools
|
||||
|
||||
jupyter_server_terminals
|
||||
|
||||
# [backend] is for installing anyscale CLI for use in the anyscale cloud.
|
||||
anyscale[backend]>=0.26.74
|
||||
@@ -0,0 +1,137 @@
|
||||
# syntax=docker/dockerfile:1.3-labs
|
||||
|
||||
# This Dockerfile is used to build the slim Ray image
|
||||
# Mainly for use on Anyscale.
|
||||
|
||||
ARG BASE_IMAGE
|
||||
FROM ${BASE_IMAGE}
|
||||
ARG PYTHON_VERSION="3.10"
|
||||
ARG PYTHON_DEPSET="python/deplocks/base_slim/ray_base_slim_py${PYTHON_VERSION}.lock"
|
||||
ARG CONSTRAINTS_FILE="python/requirements_compiled_py${PYTHON_VERSION}.txt"
|
||||
|
||||
RUN <<EOF
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
set -x
|
||||
|
||||
export DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
APT_PKGS=(
|
||||
ca-certificates
|
||||
netbase
|
||||
tzdata
|
||||
curl
|
||||
sudo
|
||||
openssh-client
|
||||
openssh-server
|
||||
rsync
|
||||
zip
|
||||
unzip
|
||||
git
|
||||
gdb
|
||||
vim-tiny
|
||||
less
|
||||
)
|
||||
|
||||
apt-get update
|
||||
apt-get upgrade -y
|
||||
apt-get install -y --no-install-recommends "${APT_PKGS[@]}"
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
useradd -ms /bin/bash -d /home/ray ray --uid 1000 --gid 100
|
||||
usermod -aG sudo ray
|
||||
echo 'ray ALL=NOPASSWD: ALL' >> /etc/sudoers
|
||||
|
||||
# Install uv
|
||||
curl -sSL -o- https://astral.sh/uv/install.sh | env UV_UNMANAGED_INSTALL="/usr/local/bin" sh
|
||||
|
||||
# Determine the architecture of the host
|
||||
if [[ "${HOSTTYPE}" =~ ^x86_64 ]]; then
|
||||
ARCH="x86_64"
|
||||
elif [[ "${HOSTTYPE}" =~ ^aarch64 ]]; then
|
||||
ARCH="aarch64"
|
||||
else
|
||||
echo "Unsupported architecture ${HOSTTYPE}" >/dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Install dynolog
|
||||
if [[ "$ARCH" == "x86_64" ]]; then
|
||||
DYNOLOG_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${DYNOLOG_TMP}"
|
||||
curl -sSL https://github.com/facebookincubator/dynolog/releases/download/v0.3.2/dynolog_0.3.2-0-amd64.deb -o dynolog_0.3.2-0-amd64.deb
|
||||
sudo dpkg -i dynolog_0.3.2-0-amd64.deb
|
||||
)
|
||||
rm -rf "${DYNOLOG_TMP}"
|
||||
fi
|
||||
|
||||
# Install azcopy
|
||||
AZCOPY_VERSION="10.30.0"
|
||||
AZCOPY_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${AZCOPY_TMP}"
|
||||
if [[ "$ARCH" == "x86_64" ]]; then
|
||||
curl -sSfL "https://github.com/Azure/azure-storage-azcopy/releases/download/v${AZCOPY_VERSION}/azcopy_linux_amd64_${AZCOPY_VERSION}.tar.gz" \
|
||||
-o- | tar -xz "azcopy_linux_amd64_${AZCOPY_VERSION}/azcopy"
|
||||
sudo mv "azcopy_linux_amd64_${AZCOPY_VERSION}/azcopy" /usr/local/bin/azcopy
|
||||
else
|
||||
curl -sSfL "https://github.com/Azure/azure-storage-azcopy/releases/download/v${AZCOPY_VERSION}/azcopy_linux_arm64_${AZCOPY_VERSION}.tar.gz" \
|
||||
-o- | tar -xz "azcopy_linux_arm64_${AZCOPY_VERSION}/azcopy"
|
||||
sudo mv "azcopy_linux_arm64_${AZCOPY_VERSION}/azcopy" /usr/local/bin/azcopy
|
||||
fi
|
||||
)
|
||||
rm -rf "${AZCOPY_TMP}"
|
||||
|
||||
# Install awscli
|
||||
AWSCLI_TMP="$(mktemp -d)"
|
||||
(
|
||||
cd "${AWSCLI_TMP}"
|
||||
curl -sfL "https://awscli.amazonaws.com/awscli-exe-linux-${ARCH}.zip" -o "awscliv2.zip"
|
||||
unzip -q awscliv2.zip
|
||||
sudo ./aws/install
|
||||
)
|
||||
rm -rf "${AWSCLI_TMP}"
|
||||
aws --version
|
||||
|
||||
EOF
|
||||
|
||||
# Switch to ray user
|
||||
USER ray
|
||||
ENV HOME=/home/ray
|
||||
WORKDIR /home/ray
|
||||
|
||||
COPY "$CONSTRAINTS_FILE" /home/ray/requirements_compiled.txt
|
||||
COPY "$PYTHON_DEPSET" /home/ray/python_depset.lock
|
||||
|
||||
RUN <<EOF
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
set -x
|
||||
|
||||
MINIFORGE_VERSION="24.11.3-0"
|
||||
|
||||
# Install miniforge
|
||||
MINIFORGE_LINK="https://github.com/conda-forge/miniforge/releases/download/${MINIFORGE_VERSION}/Miniforge3-${MINIFORGE_VERSION}-Linux-${HOSTTYPE}.sh"
|
||||
curl -sfL -o /tmp/miniforge.sh "${MINIFORGE_LINK}"
|
||||
bash /tmp/miniforge.sh -b -p /home/ray/anaconda3 # use anaconda3 to match existing images to avoid surprises.
|
||||
rm /tmp/miniforge.sh
|
||||
|
||||
/home/ray/anaconda3/bin/conda init bash
|
||||
|
||||
eval "$(/home/ray/anaconda3/bin/conda shell.bash activate)"
|
||||
/home/ray/anaconda3/bin/conda install -y "python=${PYTHON_VERSION}"
|
||||
/home/ray/anaconda3/bin/conda clean -a
|
||||
|
||||
uv pip install --system --no-cache-dir --no-deps --index-strategy unsafe-best-match \
|
||||
-r $HOME/python_depset.lock
|
||||
|
||||
anyscale --version
|
||||
|
||||
mkdir -p /tmp/supervisord
|
||||
|
||||
EOF
|
||||
|
||||
ENV PATH="/home/ray/.local/bin:/home/ray/anaconda3/bin:$PATH"
|
||||
|
||||
CMD ["bash"]
|
||||
@@ -0,0 +1,12 @@
|
||||
name: "ray-slim-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX"
|
||||
froms: ["ubuntu:22.04"]
|
||||
dockerfile: docker/base-slim/Dockerfile
|
||||
srcs:
|
||||
- python/requirements_compiled.txt
|
||||
- python/requirements_compiled_py$PYTHON_VERSION.txt
|
||||
- python/deplocks/base_slim/ray_base_slim_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- PYTHON_VERSION
|
||||
- BASE_IMAGE=ubuntu:22.04
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-slim-py$PYTHON_VERSION-cpu-base$ARCH_SUFFIX
|
||||
@@ -0,0 +1,12 @@
|
||||
name: "ray-slim-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX"
|
||||
froms: ["nvidia/cuda:$CUDA_VERSION-runtime-ubuntu22.04"]
|
||||
dockerfile: docker/base-slim/Dockerfile
|
||||
srcs:
|
||||
- python/requirements_compiled.txt
|
||||
- python/requirements_compiled_py$PYTHON_VERSION.txt
|
||||
- python/deplocks/base_slim/ray_base_slim_py$PYTHON_VERSION.lock
|
||||
build_args:
|
||||
- PYTHON_VERSION
|
||||
- BASE_IMAGE=nvidia/cuda:$CUDA_VERSION-runtime-ubuntu22.04
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-slim-py$PYTHON_VERSION-cu$CUDA_VERSION-base$ARCH_SUFFIX
|
||||
@@ -0,0 +1,10 @@
|
||||
anyscale
|
||||
packaging
|
||||
azure-identity
|
||||
adlfs[abfs]
|
||||
boto3
|
||||
google-cloud-storage
|
||||
jupyterlab
|
||||
ipywidgets
|
||||
supervisor
|
||||
smart_open[s3,gcs,azure,http]
|
||||
Executable
+39
@@ -0,0 +1,39 @@
|
||||
#!/bin/bash
|
||||
|
||||
IMAGE="1.7.0"
|
||||
|
||||
if [ $# -eq 0 ]
|
||||
then
|
||||
echo "Please Specify the release tag (i.e. 1.7.0)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
while [[ $# -gt 0 ]]
|
||||
do
|
||||
key="$1"
|
||||
case $key in
|
||||
--release-tag)
|
||||
shift
|
||||
IMAGE=$1
|
||||
;;
|
||||
*)
|
||||
echo "Usage: fix-docker-latest.sh --release-tag <TAG>"
|
||||
exit 1
|
||||
esac
|
||||
shift
|
||||
done
|
||||
|
||||
ASSUME_ROLE_CREDENTIALS=$(aws sts assume-role --role-arn arn:aws:iam::"$(aws sts get-caller-identity | jq -r .Account)":role/InvokeDockerTagLatest --role-session-name push_latest)
|
||||
|
||||
AWS_ACCESS_KEY_ID=$(echo "$ASSUME_ROLE_CREDENTIALS" | jq -r .Credentials.AccessKeyId)
|
||||
AWS_SECRET_ACCESS_KEY=$(echo "$ASSUME_ROLE_CREDENTIALS" | jq -r .Credentials.SecretAccessKey)
|
||||
AWS_SESSION_TOKEN=$(echo "$ASSUME_ROLE_CREDENTIALS" | jq -r .Credentials.SessionToken)
|
||||
|
||||
echo -e "Invoking this lambda!\nView logs at https://us-west-2.console.aws.amazon.com/cloudwatch/home?region=us-west-2#logsV2:log-groups"
|
||||
AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN AWS_SECURITY_TOKEN='' aws \
|
||||
lambda invoke --function-name DockerTagLatest \
|
||||
--cli-binary-format raw-in-base64-out \
|
||||
--cli-read-timeout 600 \
|
||||
--payload "{\"source_tag\" : \"$IMAGE\", \"destination_tag\" : \"latest\"}" /dev/stdout
|
||||
|
||||
echo -e "Please check logs before rerunning!!!!\n\nAt the time of writing, Autoscaler Images are not built.\nSo retagging errors for those images are expected!"
|
||||
@@ -0,0 +1,108 @@
|
||||
# syntax=docker/dockerfile:1.3-labs
|
||||
|
||||
ARG BASE_IMAGE
|
||||
FROM "$BASE_IMAGE"
|
||||
|
||||
COPY python/deplocks/llm/rayllm_*.lock ./
|
||||
COPY python/requirements/llm/patches/vllm-device-aware-compile-cache.patch ./
|
||||
|
||||
# vLLM version tag to use for EP kernel and DeepGEMM install scripts
|
||||
# Keep in sync with vllm version in python/requirements/llm/llm-requirements.txt
|
||||
ARG VLLM_SCRIPTS_REF="v0.24.0"
|
||||
|
||||
# Pin DeepEP to the V1 (NVSHMEM) commit that vLLM's own release image uses. The
|
||||
# install script's default drifted to DeepEP V2 ("NCCL Gin"), which needs
|
||||
# NCCL >= 2.30.4, but our image has nvidia-nccl-cu13==2.28.9 (via torch) so V2
|
||||
# fails to build. Keep in sync with DEEPEP_COMMIT_HASH in vllm's docker/Dockerfile.
|
||||
ARG DEEPEP_COMMIT_HASH="73b6ea4"
|
||||
|
||||
RUN <<EOF
|
||||
#!/bin/bash
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
PYTHON_CODE="$(python -c "import sys; v=sys.version_info; print(f'py{v.major}{v.minor}')")"
|
||||
|
||||
if [[ "${PYTHON_CODE}" == "py312" ]]; then
|
||||
CUDA_CODE=cu130
|
||||
# Use nvshmem 3.3.24 which is the default for vLLM and compatible with CUDA 13
|
||||
# https://github.com/vllm-project/vllm/blob/64ac1395e8d52e3e38910a62c7eb8524126730d8/tools/ep_kernels/install_python_libraries.sh#L14
|
||||
NVSHMEM_VER=3.3.24
|
||||
else
|
||||
echo "ray-llm supports Python 3.12 only (this image is ${PYTHON_CODE})."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Hash verification is disabled because uv pip compile generates hashes from
|
||||
# PyPI, but unsafe-best-match may download from the CUDA index which serves
|
||||
# different builds of some packages (e.g. triton). The lock file still pins
|
||||
# exact versions, so integrity is maintained through version pinning.
|
||||
uv pip install --system --no-cache-dir --no-deps \
|
||||
--index-strategy unsafe-best-match \
|
||||
--no-verify-hashes \
|
||||
-r "rayllm_${PYTHON_CODE}_${CUDA_CODE}.lock"
|
||||
|
||||
# Include the CUDA device index in vLLM's compile cache paths so a worker never
|
||||
# reloads a torch.compile artifact built for a different physical GPU.
|
||||
# TODO (jeffreywang): Remove this patch once https://github.com/vllm-project/vllm/pull/38962 lands.
|
||||
VLLM_DEVICE_AWARE_COMPILE_CACHE_PATCH="$(pwd)/vllm-device-aware-compile-cache.patch"
|
||||
VLLM_SITE_PACKAGES="$(python - <<'PY'
|
||||
import site
|
||||
import sysconfig
|
||||
from pathlib import Path
|
||||
|
||||
candidate_dirs = [
|
||||
Path(sysconfig.get_paths()["purelib"]),
|
||||
Path(sysconfig.get_paths()["platlib"]),
|
||||
*(Path(path) for path in site.getsitepackages()),
|
||||
]
|
||||
|
||||
for base_dir in dict.fromkeys(candidate_dirs):
|
||||
import_utils = base_dir / "vllm" / "utils" / "import_utils.py"
|
||||
if import_utils.exists():
|
||||
print(base_dir)
|
||||
break
|
||||
else:
|
||||
raise SystemExit("vLLM import_utils.py not found")
|
||||
PY
|
||||
)"
|
||||
(
|
||||
cd "${VLLM_SITE_PACKAGES}"
|
||||
git apply "${VLLM_DEVICE_AWARE_COMPILE_CACHE_PATCH}"
|
||||
)
|
||||
|
||||
sudo apt-get update -y && sudo apt-get install -y curl kmod pkg-config librdmacm-dev cmake
|
||||
|
||||
# Fetch and run vLLM install scripts at pinned commit
|
||||
VLLM_RAW="https://raw.githubusercontent.com/vllm-project/vllm/${VLLM_SCRIPTS_REF}"
|
||||
|
||||
# Tell uv to use system Python since the vLLM scripts use uv
|
||||
export UV_SYSTEM_PYTHON=1
|
||||
|
||||
# Set CUDA architectures for building EP kernels
|
||||
# EP kernels + DeepGEMM require Hopper+ features (matches vLLM Dockerfile)
|
||||
export TORCH_CUDA_ARCH_LIST="9.0a 10.0a"
|
||||
|
||||
# Install EP kernels (PPLX, DeepEP, and NVSHMEM)
|
||||
# Pin --deepep-ref to the V1 NVSHMEM-backend commit (see DEEPEP_COMMIT_HASH above);
|
||||
# the script's own default is the V2 NCCL-Gin backend that fails to compile here.
|
||||
curl -fsSL "${VLLM_RAW}/tools/ep_kernels/install_python_libraries.sh" | \
|
||||
bash -s -- --workspace /home/ray/llm_ep_support --nvshmem-ver ${NVSHMEM_VER} --deepep-ref ${DEEPEP_COMMIT_HASH}
|
||||
|
||||
# Install DeepGEMM
|
||||
curl -fsSL "${VLLM_RAW}/tools/install_deepgemm.sh" | bash
|
||||
|
||||
# Export installed packages
|
||||
$HOME/anaconda3/bin/pip freeze > /home/ray/pip-freeze.txt
|
||||
|
||||
sudo rm -rf /var/lib/apt/lists/*
|
||||
sudo apt-get clean
|
||||
|
||||
EOF
|
||||
|
||||
|
||||
# vLLM 0.21.0 selects the FlashInfer top-k/top-p sampler during engine initialization
|
||||
# instead of the previous PyTorch-native/Triton sampling path. The FlashInfer sampler
|
||||
# introduces longer adds a large one-time engine initialization cost. To avoid performance
|
||||
# surprises, we disable the FlashInfer sampler by default.
|
||||
ENV VLLM_USE_FLASHINFER_SAMPLER=0
|
||||
@@ -0,0 +1,11 @@
|
||||
name: "ray-llm-py$PYTHON_VERSION-cu$CUDA_VERSION-base"
|
||||
froms: ["cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base"]
|
||||
dockerfile: docker/ray-llm/Dockerfile
|
||||
srcs:
|
||||
- python/requirements.txt
|
||||
- python/deplocks/llm/rayllm_py312_cu130.lock
|
||||
- python/requirements/llm/patches/vllm-device-aware-compile-cache.patch
|
||||
build_args:
|
||||
- BASE_IMAGE=cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-llm-py$PYTHON_VERSION-cu$CUDA_VERSION-base
|
||||
@@ -0,0 +1,19 @@
|
||||
# syntax=docker/dockerfile:1.3-labs
|
||||
|
||||
ARG BASE_IMAGE
|
||||
ARG FULL_BASE_IMAGE=rayproject/ray:nightly"$BASE_IMAGE"
|
||||
FROM "$FULL_BASE_IMAGE"
|
||||
|
||||
COPY python/*requirements.txt \
|
||||
python/requirements/ml/*requirements.txt \
|
||||
python/requirements/docker/*requirements.txt ./
|
||||
COPY docker/ray-ml/install-ml-docker-requirements.sh ./
|
||||
|
||||
RUN sudo chmod +x install-ml-docker-requirements.sh \
|
||||
&& ./install-ml-docker-requirements.sh
|
||||
|
||||
# Export installed packages
|
||||
RUN $HOME/anaconda3/bin/pip freeze > /home/ray/pip-freeze.txt
|
||||
|
||||
# Make sure tfp is installed correctly and matches tf version.
|
||||
RUN python -c "import tensorflow_probability"
|
||||
@@ -0,0 +1,34 @@
|
||||
## About
|
||||
This image is an extension of the [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) image. It includes all extended requirements of `RLlib`, `Serve` and `Tune`. It is a well-provisioned starting point for trying out the Ray ecosystem. [Find the Dockerfile here.](https://github.com/ray-project/ray/blob/master/docker/ray-ml/Dockerfile)
|
||||
|
||||
## Tags
|
||||
|
||||
Images are `tagged` with the format `{Ray version}[-{Python version}][-{Platform}]`. `Ray version` tag can be one of the following:
|
||||
|
||||
| Ray version tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `latest` | The most recent Ray release. |
|
||||
| `x.y.z` | A specific Ray release, e.g. 2.9.3 |
|
||||
| `nightly` | The most recent Ray development build (a recent commit from GitHub `master`) |
|
||||
|
||||
The optional `Python version` tag specifies the Python version in the image. All Python versions supported by Ray are available, e.g. `py39`, `py310` and `py311`. If unspecified, the tag points to an image using `Python 3.9`.
|
||||
|
||||
The optional `Platform` tag specifies the platform where the image is intended for:
|
||||
|
||||
| Platform tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `-cpu` | These are based off of an Ubuntu image. |
|
||||
| `-cuXX` | These are based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the NVIDIA Docker Runtime. |
|
||||
| `-gpu` | Aliases to a specific `-cuXX` tagged image. |
|
||||
| no tag | Aliases to `-cpu` tagged images for `ray`, and aliases to ``-gpu`` tagged images for `ray-ml`. |
|
||||
|
||||
Examples tags:
|
||||
- none: equivalent to `latest`
|
||||
- `latest`: equivalent to `latest-py39-gpu`, i.e. image for the most recent Ray release
|
||||
- `nightly-py39-cpu`
|
||||
- `806c18-py39-cu112`
|
||||
|
||||
The `ray-ml` images are not built for the `arm64` (`aarch64`) architecture.
|
||||
|
||||
## Other Images
|
||||
* [`rayproject/ray`](https://hub.docker.com/repository/docker/rayproject/ray) - Ray and all of its dependencies.
|
||||
@@ -0,0 +1,21 @@
|
||||
name: "ray-ml-py$PYTHON_VERSION-cpu-base"
|
||||
froms: ["cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cpu-base"]
|
||||
dockerfile: docker/ray-ml/Dockerfile
|
||||
srcs:
|
||||
- python/requirements.txt
|
||||
- python/requirements/ml/dl-cpu-requirements.txt
|
||||
- python/requirements/ml/dl-gpu-requirements.txt
|
||||
- python/requirements/ml/core-requirements.txt
|
||||
- python/requirements/ml/data-requirements.txt
|
||||
- python/requirements/ml/rllib-requirements.txt
|
||||
- python/requirements/ml/rllib-test-requirements.txt
|
||||
- python/requirements/ml/train-requirements.txt
|
||||
- python/requirements/ml/train-test-requirements.txt
|
||||
- python/requirements/ml/tune-requirements.txt
|
||||
- python/requirements/ml/tune-test-requirements.txt
|
||||
- python/requirements/docker/ray-docker-requirements.txt
|
||||
- docker/ray-ml/install-ml-docker-requirements.sh
|
||||
build_args:
|
||||
- FULL_BASE_IMAGE=cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cpu-base
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-ml-py$PYTHON_VERSION-cpu-base
|
||||
@@ -0,0 +1,21 @@
|
||||
name: "ray-ml-py$PYTHON_VERSION-cu$CUDA_VERSION-base"
|
||||
froms: ["cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base"]
|
||||
dockerfile: docker/ray-ml/Dockerfile
|
||||
srcs:
|
||||
- python/requirements.txt
|
||||
- python/requirements/ml/dl-cpu-requirements.txt
|
||||
- python/requirements/ml/dl-gpu-requirements.txt
|
||||
- python/requirements/ml/core-requirements.txt
|
||||
- python/requirements/ml/data-requirements.txt
|
||||
- python/requirements/ml/rllib-requirements.txt
|
||||
- python/requirements/ml/rllib-test-requirements.txt
|
||||
- python/requirements/ml/train-requirements.txt
|
||||
- python/requirements/ml/train-test-requirements.txt
|
||||
- python/requirements/ml/tune-requirements.txt
|
||||
- python/requirements/ml/tune-test-requirements.txt
|
||||
- python/requirements/docker/ray-docker-requirements.txt
|
||||
- docker/ray-ml/install-ml-docker-requirements.sh
|
||||
build_args:
|
||||
- FULL_BASE_IMAGE=cr.ray.io/rayproject/ray-py$PYTHON_VERSION-cu$CUDA_VERSION-base
|
||||
tags:
|
||||
- cr.ray.io/rayproject/ray-ml-py$PYTHON_VERSION-cu$CUDA_VERSION-base
|
||||
+65
@@ -0,0 +1,65 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
# shellcheck disable=SC2139
|
||||
alias pip="$HOME/anaconda3/bin/pip"
|
||||
|
||||
sudo apt-get update \
|
||||
&& sudo apt-get install -y gcc \
|
||||
cmake \
|
||||
libgtk2.0-dev \
|
||||
libgl1-mesa-dev \
|
||||
libgl1-mesa-glx \
|
||||
libosmesa6 \
|
||||
libosmesa6-dev \
|
||||
libglfw3 \
|
||||
patchelf \
|
||||
unzip \
|
||||
unrar \
|
||||
zlib1g-dev
|
||||
|
||||
# Install requirements
|
||||
pip --no-cache-dir install -r requirements.txt -c requirements_compiled.txt
|
||||
|
||||
# Install other requirements. Keep pinned requirements bounds as constraints
|
||||
pip --no-cache-dir install \
|
||||
-c requirements.txt \
|
||||
-c requirements_compiled.txt \
|
||||
-r dl-cpu-requirements.txt \
|
||||
-r core-requirements.txt \
|
||||
-r data-requirements.txt \
|
||||
-r rllib-requirements.txt \
|
||||
-r rllib-test-requirements.txt \
|
||||
-r train-requirements.txt \
|
||||
-r train-test-requirements.txt \
|
||||
-r tune-requirements.txt \
|
||||
-r tune-test-requirements.txt \
|
||||
-r ray-docker-requirements.txt
|
||||
|
||||
|
||||
# Remove any device-specific constraints from requirements_compiled.txt.
|
||||
# E.g.: torch-scatter==2.1.1+pt20cpu or torchvision==0.15.2+cpu
|
||||
# These are replaced with gpu-specific requirements in dl-gpu-requirements.txt.
|
||||
# Also remove pandas and cupy-cuda12x pins so cudf-cu12 dependencies can resolve.
|
||||
sed "/[0-9]\+cpu/d;/[0-9]\+pt/d;/^pandas==/d;/^cupy-cuda12x==/d" "requirements_compiled.txt" > requirements_compiled_gpu.txt
|
||||
|
||||
# explicitly install (overwrite) pytorch with CUDA support
|
||||
pip --no-cache-dir install \
|
||||
-c requirements.txt \
|
||||
-c requirements_compiled_gpu.txt \
|
||||
-r dl-gpu-requirements.txt
|
||||
|
||||
sudo apt-get clean
|
||||
|
||||
# requirements_compiled.txt will be kept.
|
||||
sudo rm ./*requirements.txt requirements_compiled_gpu.txt
|
||||
|
||||
# MuJoCo Installation.
|
||||
export MUJOCO_GL=osmesa
|
||||
wget https://github.com/google-deepmind/mujoco/releases/download/2.1.1/mujoco-2.1.1-linux-x86_64.tar.gz
|
||||
mkdir -p ~/.mujoco
|
||||
mv mujoco-2.1.1-linux-x86_64.tar.gz ~/.mujoco/.
|
||||
cd ~/.mujoco || exit
|
||||
tar -xf ~/.mujoco/mujoco-2.1.1-linux-x86_64.tar.gz
|
||||
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:/root/.mujoco/mujoco-2.1.1/bin
|
||||
@@ -0,0 +1,18 @@
|
||||
# syntax=docker/dockerfile:1.3-labs
|
||||
|
||||
ARG BASE_IMAGE
|
||||
ARG FULL_BASE_IMAGE=rayproject/ray-deps:nightly"$BASE_IMAGE"
|
||||
FROM $FULL_BASE_IMAGE
|
||||
|
||||
ARG WHEEL_PATH
|
||||
ARG FIND_LINKS_PATH=".whl"
|
||||
ARG CONSTRAINTS_FILE="requirements_compiled.txt"
|
||||
|
||||
COPY $WHEEL_PATH .
|
||||
COPY $FIND_LINKS_PATH $FIND_LINKS_PATH
|
||||
|
||||
RUN $HOME/anaconda3/bin/pip --no-cache-dir install -c $CONSTRAINTS_FILE \
|
||||
`basename $WHEEL_PATH`[all] \
|
||||
--find-links $FIND_LINKS_PATH && sudo rm `basename $WHEEL_PATH`
|
||||
|
||||
RUN $HOME/anaconda3/bin/pip freeze > /home/ray/pip-freeze.txt
|
||||
@@ -0,0 +1,52 @@
|
||||
Official container images for [Ray](https://github.com/ray-project/ray).
|
||||
These images contains working Python virtual environments and required
|
||||
dependencies to run launche Ray nodes and form Ray clusters.
|
||||
everything needed to get started with running Ray. One can use the images
|
||||
for local development, or launch clusters with [Ray VM launcher][vm-launcher],
|
||||
[KubeRay][kuberay], or running them on [Anyscale][anyscale].
|
||||
|
||||
Source that builds the images are [here][source].
|
||||
|
||||
[vm-launcher]: https://docs.ray.io/en/latest/cluster/vms/index.html
|
||||
[kuberay]: https://ray-project.github.io/kuberay/
|
||||
[anyscale]: https://www.anyscale.com/
|
||||
[source]: https://github.com/ray-project/ray/blob/master/docker/ray/Dockerfile
|
||||
|
||||
## Tags
|
||||
|
||||
Images are `tagged` with the format
|
||||
`{Ray version}[-{Python version}][-{Platform}][-{Architecture}]`.
|
||||
|
||||
`Ray version` tag can be one of the following:
|
||||
|
||||
| Ray version tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `latest` | The most recent Ray release. |
|
||||
| `x.y.z` | A specific Ray release version, e.g. 2.53.0 |
|
||||
| `nightly` | The most recent Ray development build (a recent commit from GitHub `master`) |
|
||||
|
||||
The optional `Python version` tag specifies the Python version in the image.
|
||||
All Python versions supported by Ray are available, e.g. `py310`, `py311`, and
|
||||
`py312`. If unspecified, the tag points to an image using `Python 3.10`.
|
||||
|
||||
The optional `Platform` tag specifies the platform where the image is intended
|
||||
for:
|
||||
|
||||
| Platform tag | Description |
|
||||
| --------------- | ----------- |
|
||||
| `-cpu` | Based off of an Ubuntu image. |
|
||||
| `-cuXX` | Based off of an NVIDIA CUDA image with the specified CUDA version `xx`. They require the NVIDIA Docker Runtime. |
|
||||
| `-gpu` | Aliases to a specific `-cuXX` tagged image. |
|
||||
| no tag | Aliases to `-cpu` tagged images. |
|
||||
|
||||
The optional `Architecture` tag can be used to specify images for different CPU
|
||||
architectures. Currently, we support the `x86_64` (`amd64`) and `aarch64`
|
||||
(`arm64`) architectures.
|
||||
|
||||
Please note that suffixes are only used to specify `aarch64` images.
|
||||
No suffix means that it is a multi-platform image index.
|
||||
|
||||
| Platform tag | Description |
|
||||
|--------------|-----------------------------|
|
||||
| no tag | Multi-platform image index. |
|
||||
| `-aarch64` | arm64-compatible images |
|
||||
@@ -0,0 +1,16 @@
|
||||
# Updating this Lambda Function
|
||||
|
||||
1. Get Docker Retag via wget:
|
||||
```
|
||||
pushd docker/retag-lambda
|
||||
wget -q https://github.com/joshdk/docker-retag/releases/download/0.0.2/docker-retag
|
||||
popd
|
||||
```
|
||||
|
||||
2. Package this folder:
|
||||
```
|
||||
pushd docker/retag-lambda
|
||||
zip retag-lambda.zip *
|
||||
```
|
||||
|
||||
3. Head to the AWS Management console & select the `DockerTagLatest` function. Select `Upload from`, then `.zip file` and then select the zip file created in Step 2.
|
||||
@@ -0,0 +1,7 @@
|
||||
cu128
|
||||
cu125
|
||||
cu124
|
||||
cu123
|
||||
cu121
|
||||
cu118
|
||||
cu117
|
||||
@@ -0,0 +1,96 @@
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
|
||||
import boto3
|
||||
|
||||
DOCKER_USER = None
|
||||
DOCKER_PASS = None
|
||||
|
||||
|
||||
def _get_curr_dir():
|
||||
return os.path.dirname(os.path.realpath(__file__))
|
||||
|
||||
|
||||
def get_secrets():
|
||||
global DOCKER_PASS, DOCKER_USER
|
||||
secret_name = "dockerRetagLatestCredentials"
|
||||
region_name = "us-west-2"
|
||||
|
||||
session = boto3.session.Session()
|
||||
client = session.client(service_name="secretsmanager", region_name=region_name)
|
||||
get_secret_value_response = client.get_secret_value(SecretId=secret_name)
|
||||
secret_string = get_secret_value_response["SecretString"]
|
||||
dct = json.loads(secret_string)
|
||||
DOCKER_PASS = dct["DOCKER_PASS"]
|
||||
DOCKER_USER = dct["DOCKER_USER"]
|
||||
|
||||
|
||||
def retag(repo: str, source: str, destination: str) -> str:
|
||||
global DOCKER_PASS, DOCKER_USER
|
||||
if DOCKER_PASS is None or DOCKER_USER is None:
|
||||
get_secrets()
|
||||
assert (
|
||||
DOCKER_PASS is not None and DOCKER_USER is not None
|
||||
), "Docker Username or Password not set()"
|
||||
return subprocess.run(
|
||||
["./docker-retag", f"rayproject/{repo}:{source}", destination],
|
||||
env={"DOCKER_USER": DOCKER_USER, "DOCKER_PASS": DOCKER_PASS},
|
||||
)
|
||||
|
||||
|
||||
def parse_versions(version_file):
|
||||
with open(version_file) as f:
|
||||
file_versions = f.read().splitlines()
|
||||
return file_versions
|
||||
|
||||
|
||||
def lambda_handler(event, context):
|
||||
source_image = event["source_tag"]
|
||||
destination_image = event["destination_tag"]
|
||||
total_results = []
|
||||
python_versions = parse_versions(
|
||||
os.path.join(_get_curr_dir(), "python_versions.txt")
|
||||
)
|
||||
cuda_versions = parse_versions(os.path.join(_get_curr_dir(), "cuda_versions.txt"))
|
||||
for repo in ["ray", "ray-ml"]:
|
||||
results = []
|
||||
# For example tag ray:1.X-py3.7-cu112 to ray:latest-py3.7-cu112
|
||||
for pyversion in python_versions:
|
||||
source_tag = f"{source_image}-{pyversion}"
|
||||
destination_tag = f"{destination_image}-{pyversion}"
|
||||
for cudaversion in cuda_versions:
|
||||
cuda_source_tag = source_tag + f"-{cudaversion}"
|
||||
cuda_destination_tag = destination_tag + f"-{cudaversion}"
|
||||
results.append(retag(repo, cuda_source_tag, cuda_destination_tag))
|
||||
# Tag ray:1.X-py3.7 to ray:latest-py3.7
|
||||
results.append(retag(repo, source_tag, destination_tag))
|
||||
# Tag ray:1.X-py3.7-cpu to ray:latest-py3.7-cpu
|
||||
results.append(retag(repo, source_tag + "-cpu", destination_tag + "-cpu"))
|
||||
# Tag ray:1.X-py3.7-gpu to ray:latest-py3.7-gpu
|
||||
results.append(retag(repo, source_tag + "-gpu", destination_tag + "-gpu"))
|
||||
[print(i) for i in results]
|
||||
total_results.extend(results)
|
||||
|
||||
# Retag images without a python version specified (defaults to py39)
|
||||
results = []
|
||||
for repo in ["ray", "ray-ml", "ray-deps", "base-deps"]:
|
||||
# For example tag ray:1.X-cu112 to ray:latest-cu112
|
||||
for cudaversion in cuda_versions:
|
||||
source_tag = f"{source_image}-{cudaversion}"
|
||||
destination_tag = f"{destination_image}-{cudaversion}"
|
||||
results.append(retag(repo, source_tag, destination_tag))
|
||||
|
||||
# Tag ray:1.X to ray:latest
|
||||
results.append(retag(repo, source_image, destination_image))
|
||||
# Tag ray:1.X-cpu to ray:latest-cpu
|
||||
results.append(retag(repo, source_image + "-cpu", destination_image + "-cpu"))
|
||||
# Tag ray:1.X-gpu to ray:latest-gpu
|
||||
results.append(retag(repo, source_image + "-gpu", destination_image + "-gpu"))
|
||||
[print(i) for i in results]
|
||||
total_results.extend(results)
|
||||
|
||||
if all(r.returncode == 0 for r in total_results):
|
||||
return {"statusCode": 200, "body": json.dumps("Retagging Complete!")}
|
||||
else:
|
||||
return {"statusCode": 500, "body": json.dumps("Retagging Broke!!")}
|
||||
@@ -0,0 +1,4 @@
|
||||
py38
|
||||
py39
|
||||
py310
|
||||
py311
|
||||
Reference in New Issue
Block a user