From dc71406f4688462c49f77097c134b193678f3037 Mon Sep 17 00:00:00 2001
From: functionstackx <47992694+functionstackx@users.noreply.github.com>
Date: Wed, 20 May 2026 15:39:22 -0400
Subject: [PATCH] [Klaud Cold] mi300x runner: switch from --nodelist pin to
 --exclude -049

The previous --nodelist pin only allowed allocations on a hand-picked subset
(034-036, 054, 057-058) and blocked nodes that have since recovered (033,
035, 037). Switch to --exclude=chi-mi300x-049 so Slurm can pick any healthy
node; -049 stays banned (persistent /nvme_home disk-full).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 runners/launch_mi300x-amds.sh | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/runners/launch_mi300x-amds.sh b/runners/launch_mi300x-amds.sh
index 4f085d0ad..47ad12698 100644
--- a/runners/launch_mi300x-amds.sh
+++ b/runners/launch_mi300x-amds.sh
@@ -9,10 +9,9 @@ LOCK_FILE="${SQUASH_FILE}.lock"
 
 set -x
 
-# Pin to the known-good mi300x nodes; others are unavailable:
-#   chi-mi300x-033, chi-mi300x-037: down (Not responding)
-#   chi-mi300x-049:                  drained (persistent /nvme_home disk-full)
-JOB_ID=$(salloc --partition=$PARTITION --nodelist=chi-mi300x-[034-036,054,057-058].ord.vultr.cpe.ice.amd.com --gres=gpu:$TP --cpus-per-task=256 --time=180 --no-shell --job-name="$RUNNER_NAME" 2>&1 | tee /dev/stderr | grep -oP 'Granted job allocation \K[0-9]+')
+# Exclude known-bad nodes; let Slurm pick from anything else:
+#   chi-mi300x-049: drained (persistent /nvme_home disk-full)
+JOB_ID=$(salloc --partition=$PARTITION --exclude=chi-mi300x-049.ord.vultr.cpe.ice.amd.com --gres=gpu:$TP --cpus-per-task=256 --time=180 --no-shell --job-name="$RUNNER_NAME" 2>&1 | tee /dev/stderr | grep -oP 'Granted job allocation \K[0-9]+')
 
 if [ -z "$JOB_ID" ]; then
     echo "ERROR: salloc failed to allocate a job"