# GPU Observability: Get Deeper Insights into Your Droplets and DOKS Clusters

DevFeed: [GPU Observability: Get Deeper Insights into Your Droplets and DOKS Clusters](<https://devfeed.tech/articles/gpu-observability-get-deeper-insights-into-your-droplets-and-doks-clusters-19921.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/now-available-gpu-doks-observability>)

Author: Waverly Swinton

Published: 2025-11-12T20:56:52Z

Content type: release

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [GPU](<https://devfeed.tech/topics/gpu.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Digital Ocean](<https://devfeed.tech/topics/digital-ocean.md>), [monitor](<https://devfeed.tech/topics/monitor.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [amd](<https://devfeed.tech/tags/amd.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [data](<https://devfeed.tech/tags/data.md>), [droplets](<https://devfeed.tech/tags/droplets.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [network](<https://devfeed.tech/tags/network.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [observability](<https://devfeed.tech/tags/observability.md>), [performance](<https://devfeed.tech/tags/performance.md>), [product-updates](<https://devfeed.tech/tags/product-updates.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

DigitalOcean introduces basic observability metrics for GPU Droplets and DOKS clusters. The metrics cover GPU utilization, memory, temperature, power consumption, throttling, and interconnect performance, and are available through the DigitalOcean Insights UI.

## Source excerpt

We're introducing a new set of basic observability metrics for all GPU Droplets and DOKS clusters, giving you a powerful, simple way to monitor and optimize your AI workloads. Why GPU Observability Matters When running large-scale training, inference, and complex data processing--cluster performance and stability are paramount. Our new observability features are designed to give you the visibility you need to ensure effective utilization of your resources and quickly debug any performance bottlenecks. Get real-time, individual metrics from your NVIDIA and AMD GPUs and their network interfaces on critical factors like utilization, temperature, power consumption, and more--all directly within the DigitalOcean Insights UI, and with zero setup required. What's Included: New Metric Categories We've grouped the new metrics into five intuitive categories to provide a comprehensive view of your GPU and DOKS cluster health and performance: Utilization: Understand how busy your GPU cores and memory are. This includes key metrics like GPU Occupancy and Memory Utilization, allowing you to optimize your setup for peak performance live. Temperature: Monitor thermal conditions to prevent overheating and ensure stable operation under heavy load. Power: Track power consumption, which is essential for understanding GPU performance and efficiency. Throttle: Identify if your GPU is limiting its performance due to thermal, power, or voltage constraints. This is crucial for debugging sudden performance degradations. Interconnect: Gain insights into the network interface performance connecting your GPU resources. Zero Setup, No Extra Cost Observability shouldn't be a hurdle. That's why we've made this feature as seamless as possible: Default on: Observability will be enabled by default the moment you create a GPU Droplet. There is no configuration or effort required on your part. Free: These essential observability metrics are included with the AI/ML Ready images for GPU Droplets. We're com