Skip to content

Commit d0947cc

Browse files
authored
Update SLURM blueprints to point to the latest slurm-gcp release (GoogleCloudPlatform#5215)
1 parent 950a91c commit d0947cc

8 files changed

Lines changed: 10 additions & 9 deletions

File tree

examples/machine-learning/a3-highgpu-8g/a3high-slurm-blueprint.yaml

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,7 @@ vars:
2626
localssd_mountpoint: /mnt/localssd
2727
enable_nvidia_dcgm: true
2828
disk_size_gb: 200
29+
build_slurm_from_git_ref: 6.10.10
2930
#Provisioning models (set to true or fill in reservation name, pick only one)
3031
a3_reservation_name: "" # supply reservation name
3132
a3_dws_flex_enabled: false
@@ -308,7 +309,7 @@ deployment_groups:
308309
set -e -o pipefail
309310
ansible-galaxy role install googlecloudplatform.google_cloud_ops_agents
310311
ansible-pull \
311-
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C 6.10.7 \
312+
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C $(vars.build_slurm_from_git_ref) \
312313
-i localhost, --limit localhost --connection=local \
313314
-e @/var/tmp/slurm_vars.json \
314315
ansible/playbook.yml

examples/machine-learning/a3-megagpu-8g/a3mega-slurm-blueprint.yaml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@ vars:
3535
enable_login_public_ips: true
3636
enable_controller_public_ips: true
3737
localssd_mountpoint: /mnt/localssd
38-
38+
build_slurm_from_git_ref: 6.10.10
3939
#Provisioning models (set to true or fill in reservation name, pick only one)
4040
a3mega_reservation_name: "" # supply reservation name
4141
a3mega_dws_flex_enabled: false
@@ -149,7 +149,7 @@ deployment_groups:
149149
apt-get install -y git
150150
ansible-galaxy role install googlecloudplatform.google_cloud_ops_agents
151151
ansible-pull \
152-
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C 6.10.6 \
152+
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C $(vars.build_slurm_from_git_ref) \
153153
-i localhost, --limit localhost --connection=local \
154154
-e @/var/tmp/slurm_vars.json \
155155
ansible/playbook.yml

examples/machine-learning/a3-megagpu-8g/a3mega-slurm-gcsfuse-lssd-blueprint.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ vars:
3030
a3mega_maintenance_interval: ""
3131
enable_placement: false
3232
local_mount_homefs: /home
33-
build_slurm_from_git_ref: 6.10.6
33+
build_slurm_from_git_ref: 6.10.10
3434
instance_image:
3535
family: $(vars.final_image_family)
3636
project: $(vars.project_id)

examples/machine-learning/a3-ultragpu-8g/a3ultra-slurm-blueprint.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ vars:
2626
project: ubuntu-os-accelerator-images
2727
image: ubuntu-accelerator-2204-amd64-with-nvidia-570-v20260108
2828
image_build_machine_type: n2-standard-16
29-
build_slurm_from_git_ref: 6.10.6
29+
build_slurm_from_git_ref: 6.10.10
3030
# Cluster env settings
3131
# net0 and filestore ranges must not overlap
3232
net0_range: 192.168.0.0/19

examples/machine-learning/a4-highgpu-8g/a4high-slurm-blueprint.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ vars:
2626
project: ubuntu-os-accelerator-images
2727
image: ubuntu-accelerator-2204-amd64-with-nvidia-570-v20260108
2828
image_build_machine_type: n2-standard-16
29-
build_slurm_from_git_ref: 6.10.6
29+
build_slurm_from_git_ref: 6.10.10
3030
# Cluster env settings
3131
# net0 and filestore ranges must not overlap
3232
net0_range: 192.168.0.0/19

examples/machine-learning/a4x-highgpu-4g/a4xhigh-slurm-blueprint.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ vars:
2929
image_build_disk_type: hyperdisk-balanced
3030
image_disk_size_gb: 100
3131
built_image_family: slurm-ubuntu2404-accelerator-arm64-64k
32-
build_slurm_from_git_ref: 6.10.6
32+
build_slurm_from_git_ref: 6.10.10
3333
# Cluster env settings
3434
# net0 and filestore ranges must not overlap
3535
net0_range: 192.168.0.0/19

examples/machine-learning/build-service-images/a4x/blueprint.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -118,7 +118,7 @@ deployment_groups:
118118
#!/bin/bash
119119
set -e -o pipefail
120120
ansible-pull \
121-
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C 6.10.1 \
121+
-U https://github.com/GoogleCloudPlatform/slurm-gcp -C 6.10.10 \
122122
-i localhost, --limit localhost --connection=local \
123123
-e @/var/tmp/slurm_vars.json \
124124
ansible/playbook.yml

examples/machine-learning/build-service-images/shared.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ vars:
1616
region: us-central1
1717
zone: us-central1-a
1818

19-
slurm_gcp_version: 6.10.4
19+
slurm_gcp_version: 6.10.10
2020

2121
# to supply
2222
family:

0 commit comments

Comments
 (0)