HPE and NVIDIA are expanding the HPE Private Cloud AI platform for organizations that want to run AI models and agents within their own infrastructure while retaining control over data and security policies.
The platform introduces a local agent registry that allows organizations to approve the models, tools and capabilities available to each agent. It also adds workload-prioritization capabilities, controlled model access and distributed inference across systems with up to 256 GPU accelerators.
HPE Alletra Storage MP X10000 can automatically apply metadata and policies to unstructured data. In selected internal tests, HPE reported up to a 20-fold reduction in time to first token and up to a 20% increase in token throughput.
The solution includes confidential computing, encryption, infrastructure component verification and protection for models and data while they are being processed.
BTS PRO can help organizations determine whether an AI project should be implemented in the public cloud, on-premises infrastructure or a hybrid environment. The assessment covers performance, confidentiality, storage, networking, power requirements and future scalability.