File tree Expand file tree Collapse file tree 12 files changed +25
-25
lines changed
images/nccl_benchmark/scripts Expand file tree Collapse file tree 12 files changed +25
-25
lines changed Original file line number Diff line number Diff line change 59
59
uses : actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
60
60
61
61
- name : Install GO
62
- uses : actions/setup-go@0a12ed9d6a96ab950c8f026ed9f722fe0da7ef32 # v5.0.2
62
+ uses : actions/setup-go@41dfa10bad2bb2ae585af6ee5bb4d7d973ad74ed # v5.1.0
63
63
with :
64
64
go-version-file : ' go.mod'
65
65
70
70
uses : docker/setup-buildx-action@c47758b77c9736f4b2ef4073d4d51994fabfe349 # v3.7.1
71
71
72
72
- name : Log in to the Github Container registry
73
- uses : docker/login-action@1f36f5b7a2d2f7bfd524795fc966e6d88c37baa9
73
+ uses : docker/login-action@5d8785b43a795ee002a17dbf1a2235dc1997224b
74
74
with :
75
75
registry : ghcr.io
76
76
username : ${{ github.actor }}
Original file line number Diff line number Diff line change 1
- 1.14.12
1
+ 1.14.13
Original file line number Diff line number Diff line change @@ -3,4 +3,4 @@ resources:
3
3
images :
4
4
- name : controller
5
5
newName : cr.eu-north1.nebius.cloud/soperator/slurm-operator
6
- newTag : 1.14.12
6
+ newTag : 1.14.13
Original file line number Diff line number Diff line change 82
82
value : " false"
83
83
- name : SLURM_OPERATOR_WATCH_NAMESPACES
84
84
value : " *"
85
- image : controller:1.14.12
85
+ image : controller:1.14.13
86
86
imagePullPolicy : Always
87
87
name : manager
88
88
securityContext :
Original file line number Diff line number Diff line change @@ -2,5 +2,5 @@ apiVersion: v2
2
2
name : helm-slurm-cluster-storage
3
3
description : A Helm chart for Kubernetes
4
4
type : application
5
- version : " 1.14.12 "
6
- appVersion : " 1.14.12 "
5
+ version : " 1.14.13 "
6
+ appVersion : " 1.14.13 "
Original file line number Diff line number Diff line change @@ -2,5 +2,5 @@ apiVersion: v2
2
2
name : helm-slurm-cluster
3
3
description : A Helm chart for Kubernetes
4
4
type : application
5
- version : " 1.14.12 "
6
- appVersion : " 1.14.12 "
5
+ version : " 1.14.13 "
6
+ appVersion : " 1.14.13 "
Original file line number Diff line number Diff line change @@ -343,12 +343,12 @@ telemetry: {}
343
343
# otelCollectorPort: 8429
344
344
345
345
images :
346
- slurmctld : " cr.eu-north1.nebius.cloud/soperator/controller_slurmctld:1.14.12 -jammy-slurm24.05.2"
347
- slurmd : " cr.eu-north1.nebius.cloud/soperator/worker_slurmd:1.14.12 -jammy-slurm24.05.2"
348
- sshd : " cr.eu-north1.nebius.cloud/soperator/login_sshd:1.14.12 -jammy-slurm24.05.2"
349
- munge : " cr.eu-north1.nebius.cloud/soperator/munge:1.14.12 -jammy-slurm24.05.2"
350
- populateJail : " cr.eu-north1.nebius.cloud/soperator/populate_jail:1.14.12 -jammy-slurm24.05.2"
351
- ncclBenchmark : " cr.eu-north1.nebius.cloud/soperator/nccl_benchmark:1.14.12 -jammy-slurm24.05.2"
352
- slurmdbd : " cr.eu-north1.nebius.cloud/soperator/controller_slurmdbd:1.14.12 -jammy-slurm24.05.2"
353
- exporter : " cr.eu-north1.nebius.cloud/soperator/exporter:1.14.12 -jammy-slurm24.05.2"
346
+ slurmctld : " cr.eu-north1.nebius.cloud/soperator/controller_slurmctld:1.14.13 -jammy-slurm24.05.2"
347
+ slurmd : " cr.eu-north1.nebius.cloud/soperator/worker_slurmd:1.14.13 -jammy-slurm24.05.2"
348
+ sshd : " cr.eu-north1.nebius.cloud/soperator/login_sshd:1.14.13 -jammy-slurm24.05.2"
349
+ munge : " cr.eu-north1.nebius.cloud/soperator/munge:1.14.13 -jammy-slurm24.05.2"
350
+ populateJail : " cr.eu-north1.nebius.cloud/soperator/populate_jail:1.14.13 -jammy-slurm24.05.2"
351
+ ncclBenchmark : " cr.eu-north1.nebius.cloud/soperator/nccl_benchmark:1.14.13 -jammy-slurm24.05.2"
352
+ slurmdbd : " cr.eu-north1.nebius.cloud/soperator/controller_slurmdbd:1.14.13 -jammy-slurm24.05.2"
353
+ exporter : " cr.eu-north1.nebius.cloud/soperator/exporter:1.14.13 -jammy-slurm24.05.2"
354
354
mariaDB : " docker-registry1.mariadb.com/library/mariadb:11.4.3"
Original file line number Diff line number Diff line change @@ -2,5 +2,5 @@ apiVersion: v2
2
2
name : helm-soperator-crds
3
3
description : A Helm chart for Kubernetes
4
4
type : application
5
- version : 1.14.12
6
- appVersion : " 1.14.12 "
5
+ version : 1.14.13
6
+ appVersion : " 1.14.13 "
Original file line number Diff line number Diff line change @@ -2,5 +2,5 @@ apiVersion: v2
2
2
name : helm-soperator
3
3
description : A Helm chart for Kubernetes
4
4
type : application
5
- version : 1.14.12
6
- appVersion : " 1.14.12 "
5
+ version : 1.14.13
6
+ appVersion : " 1.14.13 "
Original file line number Diff line number Diff line change @@ -36,7 +36,7 @@ controllerManager:
36
36
slurmOperatorWatchNamespaces : ' *'
37
37
image :
38
38
repository : cr.eu-north1.nebius.cloud/soperator/slurm-operator
39
- tag : 1.14.12
39
+ tag : 1.14.13
40
40
imagePullPolicy : Always
41
41
resources :
42
42
limits :
Original file line number Diff line number Diff line change 77
77
78
78
job_name=" nccl_test"
79
79
ntasks_per_node=1
80
- # Get only responding nodes
81
- ready_nodes=$( sinfo --Node -h -o " %N" -r)
80
+ # Get only responding nodes uniq for all slurm partitions
81
+ ready_nodes=$( sinfo --Node -h -o " %N" -r | uniq )
82
82
83
83
run_job_on_node () {
84
84
local node=$1
Original file line number Diff line number Diff line change 2
2
package consts
3
3
4
4
const (
5
- VersionCR = "1.14.12 "
5
+ VersionCR = "1.14.13 "
6
6
)
You can’t perform that action at this time.
0 commit comments