There are two types in docker registry for deployment:
Cuda 11.8
you must use this image for the latest gpu architecture such as T4, L4, and etc. Here is the registry names: registry.gitlab.com/nodefluxio/cloud/analytics/pipelines/people-attribute-pipeline:1.1.1-cuda11.8
Cuda 10.2
you must use this image for the latest pascal gpu architecture such as P4, GTX 1060 and etc. here is the registry names registry.gitlab.com/nodefluxio/cloud/analytics/pipelines/people-attribute-pipeline:1.1.1-cuda10.2
# my global configglobal:scrape_interval:5s# Set the scrape interval to every 15 seconds. Default is every 1 minute.evaluation_interval:5s# Evaluate rules every 15 seconds. The default is every 1 minute.# scrape_timeout is set to the global default (10s).# Alertmanager configurationalerting:alertmanagers: - static_configs: - targets:# - alertmanager:9093# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.rule_files:# - "first_rules.yml"# - "second_rules.yml"# A scrape configuration containing exactly one endpoint to scrape:# Here it's Prometheus itself.scrape_configs:# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config. - job_name:"prometheus"# metrics_path defaults to '/metrics'# scheme defaults to 'http'.static_configs: - targets: ["localhost:9090", "localhost:5021", "localhost:5022", "localhost:5023", "localhost:5024", "localhost:5001", "localhost:5005", "localhost:5006"]