HPE unveils four ProLiant Gen13 servers built on AMD’s EPYC Venice chips

Photo: Jakub Pabis / Pexels

HPE unveils four ProLiant Gen13 servers built on AMD’s EPYC Venice chips

The new lineup targets agentic AI, inference and high-performance computing with up to 256 cores per socket and post-quantum security features

Hewlett Packard Enterprise has a new server family built for AI workloads.

On October 7, 2026, HPE unveiled four ProLiant Gen13 servers powered by AMD’s 6th Generation EPYC processors, codenamed Venice. The pitch is that these machines can handle demanding AI work without turning the data center into a space heater or a security liability.

What HPE is actually shipping

The headline spec is density. The Gen13 lineup supports up to 256 cores per socket with high-core-count EPYC chips, and up to 600W of TDP per socket.

TDP, or thermal design power, is the amount of heat a chip is built to produce and shed under load.

Memory gets a serious upgrade too. The servers support up to 16 memory channels of DDR5 memory running at up to 8,000 MT/s.

Advertisement

The systems also support PCIe 6.0, the latest version of the interface that connects processors to GPUs, storage and networking cards.

Four machines, four jobs

The ProLiant DL525 Gen13 is designed for CPU-based AI inference. Inference is the part of AI where a trained model actually answers questions or makes predictions, as opposed to the expensive training phase.

The ProLiant DL585a Gen13 is accelerator-optimized and supports up to eight double-wide GPUs.

Rounding out the lineup are the XD245 and XD285, which focus on advanced cooling for CPU-intensive HPC and AI workloads.

HPE says the lineup is built for hybrid workloads, spanning agentic AI, inference, analytics and modeling. Agentic AI refers to systems that can take actions and complete multistep tasks on their own, rather than simply responding to prompts.

Security gets a quantum-ready makeover

The new version of HPE iLO 8 adds automatic self-encrypting drive support, so data on storage is encrypted without someone having to remember to switch it on. It also includes readiness for post-quantum cryptography.

Post-quantum cryptography refers to encryption methods designed to hold up against future quantum computers.

Background: a long partnership with supercomputer roots

HPE says it applied lessons from its work on exascale supercomputers Frontier and El Capitan. Exascale systems can perform at least a quintillion calculations per second.

The launch also follows AMD’s earlier announcements around its EPYC 9006 series. HPE’s rollout puts that silicon into production systems aimed squarely at enterprise buyers.

Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our Editorial Policy.
HPE unveils four ProLiant Gen13 servers built on AMD’s EPYC Venice chips
HPE unveils four ProLiant Gen13 servers built on AMD’s EPYC Venice chips

The new lineup targets agentic AI, inference and high-performance computing with up to 256 cores per socket and post-quantum security features

Photo: Jakub Pabis / Pexels

Hewlett Packard Enterprise has a new server family built for AI workloads.

On October 7, 2026, HPE unveiled four ProLiant Gen13 servers powered by AMD’s 6th Generation EPYC processors, codenamed Venice. The pitch is that these machines can handle demanding AI work without turning the data center into a space heater or a security liability.

What HPE is actually shipping

The headline spec is density. The Gen13 lineup supports up to 256 cores per socket with high-core-count EPYC chips, and up to 600W of TDP per socket.

TDP, or thermal design power, is the amount of heat a chip is built to produce and shed under load.

Memory gets a serious upgrade too. The servers support up to 16 memory channels of DDR5 memory running at up to 8,000 MT/s.

Advertisement

The systems also support PCIe 6.0, the latest version of the interface that connects processors to GPUs, storage and networking cards.

Four machines, four jobs

The ProLiant DL525 Gen13 is designed for CPU-based AI inference. Inference is the part of AI where a trained model actually answers questions or makes predictions, as opposed to the expensive training phase.

The ProLiant DL585a Gen13 is accelerator-optimized and supports up to eight double-wide GPUs.

Rounding out the lineup are the XD245 and XD285, which focus on advanced cooling for CPU-intensive HPC and AI workloads.

HPE says the lineup is built for hybrid workloads, spanning agentic AI, inference, analytics and modeling. Agentic AI refers to systems that can take actions and complete multistep tasks on their own, rather than simply responding to prompts.

Security gets a quantum-ready makeover

The new version of HPE iLO 8 adds automatic self-encrypting drive support, so data on storage is encrypted without someone having to remember to switch it on. It also includes readiness for post-quantum cryptography.

Post-quantum cryptography refers to encryption methods designed to hold up against future quantum computers.

Background: a long partnership with supercomputer roots

HPE says it applied lessons from its work on exascale supercomputers Frontier and El Capitan. Exascale systems can perform at least a quintillion calculations per second.

The launch also follows AMD’s earlier announcements around its EPYC 9006 series. HPE’s rollout puts that silicon into production systems aimed squarely at enterprise buyers.

Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our Editorial Policy.