diff --git a/benchmark/cluster/vgg16/run_vgg_dist.sh b/benchmark/cluster/vgg16/run_vgg_dist.sh
new file mode 100644
index 0000000000000000000000000000000000000000..8c0501439e9d5fa175f5aa9b62d286e690a10904
--- /dev/null
+++ b/benchmark/cluster/vgg16/run_vgg_dist.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+
+# Update to point to the source file.
+VGG_SRC="vgg16_fluid.py"
+
+export TRAINING_ROLE=PSERVER
+export TRAINERS=2
+export POD_IP=127.0.0.1
+export PADDLE_INIT_PORT=6174
+MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 &
+
+# Need to wait for the ps to start first.
+sleep 10
+echo "done start ps"
+
+export TRAINING_ROLE=TRAINER
+export TRAINERS=2
+export POD_IP=127.0.0.1
+export PADDLE_INIT_PORT=6174
+CUDA_VISIBLE_DEVICES=4 MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 --device=GPU --task_index=0 &
+CUDA_VISIBLE_DEVICES=5 MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 --device=GPU --task_index=1 &
diff --git a/benchmark/cluster/vgg16/vgg16_fluid.py b/benchmark/cluster/vgg16/vgg16_fluid.py
index 12c739480801a7f422773be6dad7dfe002999284..6c47f6535c3cfc31ba165ccec07ac95a9bfd0a7f 100644
--- a/benchmark/cluster/vgg16/vgg16_fluid.py
+++ b/benchmark/cluster/vgg16/vgg16_fluid.py
@@ -11,25 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""VGG16 benchmark in Fluid
-
-# Single trainer, single PS on a single machine.
-VGG_SRC="${CODE_DIR}/vgg16_fluid.py"
-export TRAINING_ROLE=PSERVER
-export TRAINERS=1
-export POD_IP=127.0.0.1
-export PADDLE_INIT_PORT=6174
-MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 &
-sleep 10  # wait for PS to start.
-export TRAINING_ROLE=TRAINER
-MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 --device=GPU &
-
-# To run multiple trainers on a single machine
-# change TRAINERS=2 and launch 2 trainers.
-# CUDA_VISIBLE_DEVICES=4 MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 --device=GPU --task_index=0 &
-# CUDA_VISIBLE_DEVICES=5 MKL_NUM_THREADS=1 python -u ${VGG_SRC} --local 0 --ps_host=127.0.0.1:6174 --trainer_hosts=127.0.0.1:6174 --device=GPU --task_index=1 &
-"""
-
+"""VGG16 benchmark in Fluid"""
 from __future__ import print_function
 
 import sys