Infrastructure · Software component

Custom Metrics Adapter

Software componentInfrastructureInfrastructurearc:CustomMetricsAdapter

A bridge that exposes collected application metrics through the container orchestrator's metrics API so autoscalers can scale on inference-specific signals.

Responsibility. Makes monitoring-system metrics consumable by the orchestrator's autoscaler.

Also known as: Custom metrics API, Custom metrics exporter

Direct neighbourhood (hover for relationship types)

Relationships

receives data from dynamic

Metrics Collector Ch4.5 Ref4.03

sends data to dynamic

Metric-Driven Autoscaler Ch4.5 Ref4.03 +1

Design guidance

SHOULD expose queue depth, inference latency and business metrics as scaling signals beyond built-in CPU/memory metrics.

Classification

Technologies: Kubernetes custom metrics APIPrometheus

Sources

Ch4.5: T. Nguyen, "NVIDIA NIM and Triton Inference Server," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.5. ISBN: 9798244538229.
Ref4.03: M. Zhang, J. Wyman, I. M. Bhosale, and W. Tan, "Scaling LLMs with NVIDIA Triton and NVIDIA TensorRT-LLM using Kubernetes," NVIDIA Technical Blog, Oct. 22, 2024. [Online]. Available: https://developer.nvidia.com/blog/scaling-llms-with-nvidia-triton-and-nvidia-tensorrt-llm-using-kubernetes/
Ref7.17: "Scaling Agentic AI Systems: Patterns and Strategies," unpublished reference note (17-Scalability-Patterns.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note