fix: use SLURM_SUBMIT_DIR to locate repo root under sbatch

This commit is contained in:
2026-07-17 06:13:28 -04:00
parent 9bb09a44d4
commit 3dcc7d9899
+8 -1
View File
@@ -25,7 +25,14 @@
set -euo pipefail
cd "$(dirname "$0")/.."
# sbatch 会把脚本拷贝到 Slurm spool 目录执行,$0 不指向仓库路径——须用
# SLURM_SUBMIT_DIR(提交命令时所在目录,即仓库根)定位;本地直跑时回退 dirname。
cd "${SLURM_SUBMIT_DIR:-$(dirname "$0")/..}"
echo "== 工作目录: $(pwd) =="
[[ -f "config/train_videomme.yaml" ]] || {
echo "错误: 当前目录不是仓库根(找不到 config/train_videomme.yaml)。请在仓库根目录提交 gpu-sbatch。" >&2
exit 1
}
echo "== Slurm Job: ${SLURM_JOB_ID:-unknown} | CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES:-unset} =="
nvidia-smi || true