Bryan Thompson, HPE | VMware Explore 2023
summary
HPE says it is shipping LLMs as a service on GreenLake, tying model hosting to on-prem hardware including Gen11 servers with Nvidia GPU support and a GreenLake for VMware Cloud Foundation offering; it emphasizes workload placement between private and public clouds, EKS Anywhere support, and edge deployments using small form factors plus zero-touch provisioning to avoid truck rolls — positioning an evergreen, consumption-priced cloud operating model that stays patched and scales capacity on demand.
AI-written summary · about
