Skip to content

Commit 28ae46b

Browse files
fix: add excluded nodes in MI325 cluster
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
1 parent abdbff6 commit 28ae46b

1 file changed

Lines changed: 2 additions & 1 deletion

File tree

runners/launch_mi325x-amds.sh

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,8 @@ scancel_sync() {
2828
# chi-mi325x-pod1-121: enroot-aufs2ovlfs setcap fails on this node's NFS-backed
2929
# squash dir; container image import never completes
3030
# (root-caused via #1467/#1468/#1469 sweep failures).
31-
export SLURM_EXCLUDE_NODES="${SLURM_EXCLUDE_NODES:-}"
31+
export SLURM_EXCLUDE_NODES="${SLURM_EXCLUDE_NODES:-chi-mi325x-pod1-021.ord.vultr.cpe.ice.amd.com,chi-mi325x-pod1-027.ord.vultr.cpe.ice.amd.com,chi-mi325x-pod1-028.ord.vultr.cpe.ice.amd.com,chi-mi325x-pod1-030.ord.vultr.cpe.ice.amd.com,chi-mi325x-pod1-121.ord.vultr.cpe.ice.amd.com}"
32+
3233

3334
if [[ "$IS_MULTINODE" == "true" ]]; then
3435
set -x

0 commit comments

Comments
 (0)