Skip to content

NO-ISSUE: feat(deploy): add AMD GPU usage monitor dashboard#71

Merged
hhk7734 merged 2 commits intomainfrom
amd-gpu-usage-monitor
Feb 26, 2026
Merged

NO-ISSUE: feat(deploy): add AMD GPU usage monitor dashboard#71
hhk7734 merged 2 commits intomainfrom
amd-gpu-usage-monitor

Conversation

@seongsu-dev
Copy link
Copy Markdown
Contributor

No description provided.

…tion

- Introduced a new JSON file for the AMD GPU usage monitor dashboard, featuring various panels and configurations for visualizing GPU metrics using Prometheus as the data source.
- The dashboard includes text panels, stat panels, and configurations for displaying GPU activity and usage statistics, enhancing monitoring capabilities for AMD GPUs in the MoAI Inference Framework.
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new Grafana dashboard JSON to the Helm chart so MIF deployments can visualize AMD GPU usage (via Prometheus gpu_gfx_activity) per host/GPU.

Changes:

  • Add AMD GPU Usage Monitor Grafana dashboard JSON under the chart’s provisioned dashboards directory.

Comment thread deploy/helm/moai-inference-framework/files/dashboards/amd-gpu-usage-monitor.json Outdated
Comment thread deploy/helm/moai-inference-framework/files/dashboards/amd-gpu-usage-monitor.json Outdated
@hhk7734
Copy link
Copy Markdown
Member

hhk7734 commented Feb 26, 2026

설치되는지 테스트되었나요?

@seongsu-dev
Copy link
Copy Markdown
Contributor Author

설치되는지 테스트되었나요?

claude에 문제없는지만 질문했었습니다. kind에서 테스트해보겠습니다 🙇

…uration

- Removed the ID field from the dashboard JSON to streamline configuration.
- Specified the data source type as "prometheus" for better clarity.
- Changed the refresh rate from "auto" to "30s" to ensure consistent data updates.
@seongsu-dev
Copy link
Copy Markdown
Contributor Author

kind 클러스터에 설치해보니 정상적으로 추가됩니다
image

@hhk7734 hhk7734 merged commit 6bb5871 into main Feb 26, 2026
3 checks passed
@hhk7734 hhk7734 deleted the amd-gpu-usage-monitor branch February 26, 2026 07:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants