update

Dockerfile.jupyterhub

@@ -69,7 +69,7 @@ wget -qO- https://cloud.r-project.org/bin/linux/ubuntu/marutter_pubkey.asc | sud
 sudo add-apt-repository "deb https://cloud.r-project.org/bin/linux/ubuntu $(lsb_release -cs)-cran40/"
 apt-get update
 apt install --no-install-recommends r-base
-sudo wget "https://download2.rstudio.org/server/$(lsb_release -cs)/amd64/rstudio-server-2023.06.1-524-amd64.deb" -O /tmp/rstudio-server.deb
+sudo wget "https://download2.rstudio.org/server/$(lsb_release -cs)/amd64/rstudio-server-2024.09.1-394-amd64.deb" -O /tmp/rstudio-server.deb
 sudo chmod +x /tmp/rstudio-server.deb 
 sudo gdebi -n /tmp/rstudio-server.deb
 sudo rm -rf /tmp/rstudio-server.deb

spawnerdockerfile/Dockerfile.base-notebook

@@ -110,7 +110,7 @@ python3 -m pip install aiohttp -i http://mirrors.aliyun.com/pypi/simple/ --trust
 python3 -m pip install jupyterhub jupyterlab notebook radian pycurl aiohttp jupyter-rsession-proxy ipykernel>=6.25.0 jupyterlab-language-pack-zh-CN jupyterlab-git jupyterlab-system-monitor jupyter_nbextensions_configurator jupyter_contrib_nbextensions jupyterlab_widgets jupyterlab-drawio jupyterlab-spreadsheet-editor jupyterlab-cell-flash jedi-language-server jupyterlab_code_formatter jupyterlab-spellchecker jupyterlab_vim nbresuse ipydrawio jedi ipympl black isort theme-darcula ipywidgets tensorboard jupyterlab_latex jupyter_bokeh autopep8 xeus-python jupyterlab-lsp python-lsp-server dockerspawner jupyterhub-nativeauthenticator lckr_jupyterlab_variableinspector -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
 EOT
 
-ARG RSERVER_VERSION="rstudio-server-2024.04.1-748-amd64.deb"
+ARG RSERVER_VERSION="rstudio-server-2024.09.1-394-amd64.deb"
 ENV RSERVER_VERSION=${RSERVER_VERSION}
 RUN <<EOT
 #!/bin/bash

spawnerdockerfile/Dockerfile.ngc

@@ -17,23 +17,19 @@ SHELL ["/bin/bash", "-c"]
 
 # https://network.nvidia.com/products/infiniband-drivers/linux/mlnx_ofed/
 ENV MLNX_OFED_VERSION=23.10-3.2.2.0 
+ENV STAGE_DIR=/tmp
 RUN <<EOT
 #!/bin/bash
-# SYSTEM_NAME=$(lsb_release -cs) # 查看发行版本
+# install Mellanox OFED prepare
-# Pre-build **latest** DeepSpeed, so it would be ready for testing (otherwise, the 1st deepspeed test will timeout)
+apt-get update
-python3 -m pip uninstall -y deepspeed
+apt install -y libnvidia-compute-535
-# This has to be run (again) inside the GPU VMs running the tests.
+apt-get install -y pciutils tk kmod libusb-1.0-0 tcl chrpath libpci3 bison lsof graphviz ethtool swig udev libltdl-dev libelf1 libmnl0 debhelper flex libfuse2
-# The installation works here, but some tests fail, if we do not pre-build deepspeed again in the VMs running the tests.
-# TODO: Find out why test fail. install deepspeed
-# DS_BUILD_CPU_ADAM=${DS_BUILD_CPU_ADAM} DS_BUILD_FUSED_ADAM={DS_BUILD_FUSED_ADAM} python3 -m pip install "deepspeed<=0.14.0" --global-option="build_ext" --global-option="-j8" --no-cache -v --disable-pip-version-check 2>&1
-# from https://github.com/huggingface/transformers/blob/main/docker/transformers-pytorch-deepspeed-latest-gpu/Dockerfile install deepspeed fail 
-# reference deepspeed install from https://github.com/microsoft/DeepSpeed/blob/master/docker/Dockerfile
-# install deepspeed prepare
 # install Mellanox OFED
 mkdir -p ${STAGE_DIR}
-wget -q -O - http://www.mellanox.com/downloads/ofed/MLNX_OFED-${MLNX_OFED_VERSION}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64.tgz | tar xzf -
+wget http://www.mellanox.com/downloads/ofed/MLNX_OFED-${MLNX_OFED_VERSION}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64.tgz -O ${STAGE_DIR}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64.tgz
-cd MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64
+tar xzf ${STAGE_DIR}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64.tgz -C ${STAGE_DIR}
-./mlnxofedinstall --user-space-only --without-fw-update --all -q 
+cd ${STAGE_DIR}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64
+./mlnxofedinstall --user-space-only --without-fw-update --all -q > ${STAGE_DIR}/mlnxofedinstall.log 2>&1
 cd ${STAGE_DIR} 
 rm -rf ${STAGE_DIR}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu22.04-x86_64*
 EOT
@@ -86,7 +82,6 @@ pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=
 pip install git+https://github.com/huggingface/transformers
 EOT
 
-ENV STAGE_DIR=/tmp
 RUN <<EOT
 #!/bin/bash
 git clone https://github.com/microsoft/DeepSpeed-Kernels.git ${STAGE_DIR}/DeepSpeed-Kernels

spawnerdockerfile/Dockerfile.rserver

@@ -104,7 +104,7 @@ npm install -g configurable-http-proxy
 python3 -m pip install jupyterhub jupyterlab notebook radian pycurl jupyter-rsession-proxy ipykernel>=6.25.0 jupyterlab-language-pack-zh-CN jupyterlab-git jupyterlab-system-monitor jupyter_nbextensions_configurator jupyter_contrib_nbextensions jupyterlab_widgets jupyterlab-drawio jupyterlab-spreadsheet-editor jupyterlab-cell-flash jedi-language-server jupyterlab_code_formatter jupyterlab-spellchecker jupyterlab_vim nbresuse ipydrawio jedi ipympl black isort theme-darcula ipywidgets tensorboard jupyterlab_latex jupyter_bokeh autopep8 xeus-python jupyterlab-lsp python-lsp-server nglview dockerspawner jupyterhub-nativeauthenticator lckr_jupyterlab_variableinspector -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
 EOT
 
-ARG RSERVER_VERSION="rstudio-server-2024.04.1-748-amd64.deb"
+ARG RSERVER_VERSION="rstudio-server-2024.09.1-394-amd64.deb"
 ENV RSERVER_VERSION=${RSERVER_VERSION}
 RUN <<EOT
 #!/bin/bash

spawnerdockerfile/README.md

@@ -29,7 +29,8 @@ NCCL_IB_DISABLE=0
 ## test command
 
 docker run -it --rm --network=host --privileged --ipc=host --ulimit memlock=-1 --gpus all hotwa/notebook:ngc
-docker run --rm -it --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 hotwa/notebook:ngc /bin/bash
+docker run --rm -it --network=host --privileged --ipc=host --gpus all --ulimit memlock=-1 stack=67108864 hotwa/notebook:ngc /bin/bash
+docker run --rm -it --privileged --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 hotwa/notebook:ngc /bin/bash
 
 ```shell
 nvidia-smi
@@ -120,16 +121,23 @@ pytorch-notebook
 
 ```shell
 git clone https://github.com/jupyter/docker-stacks.git
-cd docker-stacks/images/docker-stacks-foundation
+cd spawnerdockerfile/docker-stacks/images/docker-stacks-foundation
-docker buildx build --build-arg ROOT_CONTAINER=nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 -t quay.io/hotwa/docker-stacks-foundation:latest . --load # docker pull nvidia/cuda:12.4.1-devel-ubuntu22.04
+nerdctl --namespace buildkit build --no-cache --build-arg ROOT_IMAGE=nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 -t quay.io/hotwa/docker-stacks-foundation:latest .
+nerdctl --namespace buildkit build --build-arg ROOT_IMAGE=nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 -t quay.io/hotwa/docker-stacks-foundation:latest .
+nerdctl --namespace buildkit push quay.io/hotwa/docker-stacks-foundation:latest
+docker buildx build --build-arg ROOT_IMAGE=nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 -t quay.io/hotwa/docker-stacks-foundation:latest . --load # docker pull nvidia/cuda:12.4.1-devel-ubuntu22.04
 cd ../base-notebook
 docker buildx build --build-arg OWNER=hotwa -t quay.io/hotwa/base-notebook:latest . --load
+nerdctl build --build-arg OWNER=hotwa -t quay.io/hotwa/base-notebook:latest .
 cd ../minimal-notebook/
 docker buildx build --build-arg OWNER=hotwa -t quay.io/hotwa/minimal-notebook:latest . --load
+nerdctl build --build-arg OWNER=hotwa -t quay.io/hotwa/minimal-notebook:latest .
 cd ../scipy-notebook
 docker buildx build --build-arg OWNER=hotwa -t quay.io/hotwa/scipy-notebook:latest . --load
+nerdctl build --build-arg OWNER=hotwa -t quay.io/hotwa/scipy-notebook:latest .
 cd ../pytorch-notebook
 docker buildx build --build-arg OWNER=hotwa -t quay.io/hotwa/pytorch-notebook:latest . --load
+nerdctl build --build-arg OWNER=hotwa -t quay.io/hotwa/pytorch-notebook:latest .
 ```
 
 # 然后构建自己的基础镜像

spawnerdockerfile/docker-compose_ngc.yml

@@ -45,7 +45,7 @@ services:
     # tty: true
     # stdin_open: true
     restart: unless-stopped
-    image: hotwa/notebook:ngc
+    image: quay.io/hotwa/ngc:latest
     privileged: true
     ipc: host
     network_mode: host