From 43d2784ac3312d1df8ea3b0d0596464ea9cdc44d Mon Sep 17 00:00:00 2001 From: Ran Lu Date: Sat, 21 Sep 2024 00:25:57 -0400 Subject: [PATCH 1/3] Upgrade the nvidia kernel module --- cloud/google/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloud/google/common.py b/cloud/google/common.py index e2c9e8fb..818a4bc0 100644 --- a/cloud/google/common.py +++ b/cloud/google/common.py @@ -24,7 +24,7 @@ curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | tee /etc/apt/sources.list.d/nvidia-docker.list add-apt-repository -y ppa:graphics-drivers/ppa apt-get update -y -DEBIAN_FRONTEND=noninteractive apt-get -y -o Dpkg::Options::="--force-confdef" -o Dpkg::Options::="--force-confold" install nvidia-headless-530 nvidia-utils-530 nvidia-container-toolkit +DEBIAN_FRONTEND=noninteractive apt-get -y -o Dpkg::Options::="--force-confdef" -o Dpkg::Options::="--force-confold" install nvidia-headless-560 nvidia-utils-560 nvidia-container-toolkit systemctl restart docker ''' From bc4e14676e73ed61909d45fa740f508bfe294d6e Mon Sep 17 00:00:00 2001 From: Ran Lu Date: Sat, 21 Sep 2024 00:26:50 -0400 Subject: [PATCH 2/3] Update repo for nvidia-container-toolkit --- cloud/google/common.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/cloud/google/common.py b/cloud/google/common.py index 818a4bc0..f2eaa6b8 100644 --- a/cloud/google/common.py +++ b/cloud/google/common.py @@ -20,8 +20,10 @@ echo ##### Set up NVidia ############################################################# # Add the package repositories distribution=$(. /etc/os-release;echo $ID$VERSION_ID) -curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | apt-key add - -curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | tee /etc/apt/sources.list.d/nvidia-docker.list +curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg +curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \ +sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \ +sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list add-apt-repository -y ppa:graphics-drivers/ppa apt-get update -y DEBIAN_FRONTEND=noninteractive apt-get -y -o Dpkg::Options::="--force-confdef" -o Dpkg::Options::="--force-confold" install nvidia-headless-560 nvidia-utils-560 nvidia-container-toolkit From 89a0442a376a4a1ae94b7217259efc223b7afca9 Mon Sep 17 00:00:00 2001 From: Ran Lu Date: Sat, 21 Sep 2024 00:27:23 -0400 Subject: [PATCH 3/3] Switch OS to ubuntu 24.04 --- cloud/google/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cloud/google/common.py b/cloud/google/common.py index f2eaa6b8..2b46eb5d 100644 --- a/cloud/google/common.py +++ b/cloud/google/common.py @@ -101,7 +101,7 @@ def GenerateAirflowVar(context, hostname_manager): def GenerateBootDisk(diskSizeGb, diskType=None): boot_disk = GenerateDisk(diskSizeGb=diskSizeGb, diskType=diskType) boot_disk["boot"] = True - boot_disk["initializeParams"]["sourceImage"] = GlobalComputeUrl("ubuntu-os-cloud", "images", "family/ubuntu-2204-lts") + boot_disk["initializeParams"]["sourceImage"] = GlobalComputeUrl("ubuntu-os-cloud", "images", "family/ubuntu-2404-lts-amd64") return boot_disk