Infrastructure · Data artifact

Uniform GPU Partition Layout

Data artifactInfrastructureInfrastructurearc:UniformGPUPartitionLayout

A GPU partition layout that applies one identical partition profile to every GPU in the cluster, exposing interchangeable partition resources.

Responsibility. Declares a homogeneous partition geometry so any partition satisfies any matching request.

Also known as: Strategy single, all-1g.10gb

Variant of GPU Partition Layout abstract

When to choose. Choose for homogeneous workloads and SaaS platforms with many similar-sized tenants where operational simplicity is the priority.

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

GPU Partition Ch7.6

alternative to variability

Design guidance

SHOULD reserve spare partitions for redundancy and rolling updates.

Quantitative guidance

As stated by the sources; verify before use.

8 A100-80GB at 7x1g.10gb expose 56 instances: 50 tenants plus 6 spares (Ch7.6).
10 GPUs at 1g.10gb expose 70 identical devices (Ch7.6).

Classification

Quality attributes: Maintainability (ISO/IEC 25010)

Sources

Ch7.6: T. Nguyen, "Multi-Instance GPU," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.6. ISBN: 9798244538229.