A bank is planning to deploy an AI inference solution at its branch locations. The solution must support workloads that require a balance of compute, memory, and potential GPU acceleration, and it must be suitable for installation by nontechnical onsite resources. The requirements are:
high availability of the chassis management plane.
support for up to 768 GB of memory for in-memory model storage and processing
remote server launch requiring no on-site IT staff
use of Cisco Intersight for SaaS-based infrastructure lifecycle management
Which solution meets the requirements?
Submit