startup_inf_script.sh

#!/bin/bash

# GPU Agent
git clone https://github.com/b0noI/gcp-gpu-utilization-metrics.git
cd gcp-gpu-utilization-metrics
git checkout 6e62ea324bf097817474b51119786e8222dd9fdf
pip install -r ./requirenments.txt
cp ./report_gpu_metrics.py /root/report_gpu_metrics.py

cat <<-EOH > /lib/systemd/system/gpu_utilization_agent.service
[Unit]
Description=GPU Utilization Metric Agent

[Service]
Type=simple
PIDFile=/run/gpu_agent.pid
ExecStart=/bin/bash --login -c '/usr/bin/python /root/report_gpu_metrics.py'
User=root
Group=root
WorkingDirectory=/
Restart=always

[Install]
WantedBy=multi-user.target
EOH

systemctl daemon-reload
systemctl --no-reload --now enable /lib/systemd/system/gpu_utilization_agent.service

cat <<-EOH > /lib/systemd/system/tfserve.service
[Unit]
Description=Inf Logic

[Service]
Type=simple
PIDFile=/run/tfserve_agent.pid
ExecStart=/bin/bash --login -c '/usr/local/bin/tensorflow_model_server --model_base_path=/root/resnet_v2_int8_NCHW/ --rest_api_port=8888'
User=root
Group=root
WorkingDirectory=/
Restart=always

[Install]
WantedBy=multi-user.target
EOH

gsutil cp gs://dl-platform-public-content/blog-posts/t4-release/model.tar.gz /root/model.tar.gz
tar -xzvf /root/model.tar.gz -C /root

systemctl daemon-reload
systemctl --no-reload --now enable /lib/systemd/system/tfserve.service