Skip to content

Commit d99e07c

Browse files
committed
Install DCGM exporter in A3 Mega image
1 parent 9f1e94c commit d99e07c

File tree

2 files changed

+5
-0
lines changed

2 files changed

+5
-0
lines changed

.github/workflows/gcp-a3mega-image.yml

+1
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@ name: Build GCP A3 Mega VM image
22

33
on:
44
- workflow_dispatch
5+
- push
56

67
env:
78
PACKER_VERSION: "1.9.2"

scripts/packer/gcp-a3mega-image.json

+4
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,10 @@
1919
{
2020
"type": "shell",
2121
"inline": [
22+
"sudo rm /etc/apt/sources.list.d/ar_us_apt_pkg_dev_projects_gce_ai_infra.list",
23+
"sudo apt-get update",
24+
"sudo apt-get install -y --no-install-recommends datacenter-gpu-manager-4-proprietary datacenter-gpu-manager-exporter",
25+
"sudo systemctl disable google-cloud-ops-agent.service",
2226
"gcloud -q auth configure-docker us-docker.pkg.dev",
2327
"docker pull us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpxo/tcpgpudmarxd-dev:v1.0.14",
2428
"docker pull us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpxo/nccl-plugin-gpudirecttcpx-dev:v1.0.8-1"

0 commit comments

Comments
 (0)