NVIDIA GPU metrics dashboard 878878
1/17/2020
1/17/2020
1
AWSDockerHost Metrics
>=6.5.2
Prometheus
This dashboard displays GPU metrics collected from NVIDIA dcgm-exporter via a metric endpoint added to Prometheus. A separate endpoint is added to Prometheus via a scrape configmap as shown in the screenshot. You will need to update the Prometheus url in the datasource section for Grafana the display metrics. You can find all the steps here
Get Dashboard✕
Download
Copy to Clipboard
Used Metrics 88
dcgm_gpu_temp
dcgm_power_usage
dcgm_sm_clock
dcgm_memory_clock
dcgm_gpu_utilization
dcgm_mem_copy_utilization
dcgm_fb_used
dcgm_fb_free