Agentic AI Reference Architecture

Model Serving · Model asset

Interchange Model Graph

Model assetModel ServingModelsarc:InterchangeModelGraph

A framework-neutral serialised computation graph (layers, operations, control flow and weights) of a trained model, used as input to quantization and engine compilation.

Responsibility. Carries a trained model between the training framework and the optimisation toolchain in a standard format.

Also known as: ONNX model, Intermediate representation

is optimized byis produced byModel Quantizer: is optimized byModel QuantizerModel Graph Exporter: is produced byModel Graph Exporter
Direct neighbourhood (hover for relationship types)

Relationships

is optimized by lifecycle

is produced by lifecycle

Classification

Technologies
ONNX
Quality attributes
Flexibility (ISO/IEC 25010)

Sources

  1. Ch7.4: T. Nguyen, "TensorRT-LLM Fundamentals and Quantization," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.4. ISBN: 9798244538229.
  2. Ref7.01: NVIDIA, "Best practices," NVIDIA TensorRT Documentation. Accessed: Sep. 27, 2026. [Online]. Available: https://docs.nvidia.com/deeplearning/tensorrt/latest/performance/best-practices.html