AI Center Considerations

On top of the core service requirements that are part of full platform requirements, AI Center requires additional resources, depending on the models that you want to run or train.

The following table describes the additional resources AI Center needs. In this table, Data Disk is needed on all server nodes. This is not needed on agent nodes.

Use	CPU	RAM (GiB)	GPU	Disk (GiB)
Minimum for serving (ML Skill, one replica)	0.6	2	0	20 OS Cluster Disk
Minimum for Training (Pipeline)	1	4	0	20 OS Cluster Disk 105 Data Disk
DU model Serving (ML Skill, one replica)	1	4	0	20 OS Cluster Disk
DU model Training	2	24	Strongly recommended	20 OS Cluster Disk 105 Data Disk

The following table describes the required resources for small and average AI Center implementations. Note that these numbers are general guidance. In this table, Data Disk is needed on all server nodes. This is not needed on agent nodes.

Use	CPU	RAM (GiB)	GPU	Disk (GiB)
Small implementation: 3 models served 1 concurrent pipelines	4	32	0	80 OS Disk 200 Data Disk
Average implementation: 5 models served 2 concurrent pipelines DU model training	8	52	Strongly recommended	150 OS Disk 300 Data Disk