# DPUs & SmartNICs

Canonical URL: https://aicomputexos.com/en/products/item/dpu/

Language: en

Select DPUs or SmartNICs to offload networking, storage and security workloads, with the software stack, network protocols and server platform confirmed together.

## DPUs & SmartNICs

DPUs and SmartNICs

Select DPUs or SmartNICs to offload networking, storage and security workloads, with the software stack, network protocols and server platform confirmed together.

- Applications

Infrastructure workload offload, network virtualization, storage networking and security processing.

- Supply Scope

Data processing unit (DPU) cards · Programmable SmartNICs · Network and storage offload adapters

- Information for an Inquiry

Complete model or configuration, quantity, equipment location or destination, and required dates. Quote, condition, accessories and warranty are confirmed separately.

## From application to equipment list

Specification examples help define requirements. Support depends on the exact model, platform documentation and supplier information.

### Common Types & Supporting Components

- Data processing unit (DPU) cards

- Programmable SmartNICs

- Network and storage offload adapters

- Integrated server configurations

Infrastructure workload offload, network virtualization, storage networking and security processing.

### Key Specifications

- Functionality

Networking, storage or security tasks to offload

- Interface

PCIe or OCP form factor and port configuration

- Networking

Protocols, port speeds and matching switches

- Software

SDK, firmware, drivers and deployment licenses

- Platform

CPU architecture, system version and cooling airflow

- Delivery Scope

Cards, brackets, modules, cables and licensing scope

### Four Checks Before Purchasing

- 01Check functionality against the application and software stack

- 02Confirm firmware, drivers and management interfaces

- 03Check server dimensions, airflow and port modules

- 04Specify licenses, development tools and accessory requirements

## Coordinate the product, accessories and delivery

Submit a complete model or project bill of materials so we can check compatibility, main units, accessories, quantities, lead times and destination. Compare supply sources, volume purchasing and phased delivery for the actual requirement.

Source, condition, specifications, tests, warranty and after-sales scope are confirmed separately in the quotation and order. This page describes purchasing scope; actual models, quantities and prices depend on the inquiry result.

## Related Equipment & Parts

Check the platform and application together to avoid mismatches between main equipment and accessories.

### Data Center GPUs

Data-center GPUs

Source data center GPUs for AI training, inference, simulation and parallel computing, with the configuration matched to workload, accelerator memory and server platform.

- PCIe GPU cards

- GPU modules supplied with a compatible server

- Single- and multi-GPU configurations

Check: workload · accelerator memory · platform

### AI Accelerators

AI accelerator cards

Select accelerator cards for AI inference and specialized workloads after confirming the processor architecture, software toolchain and model deployment requirements.

- PCIe inference accelerators

- Dedicated AI accelerator cards

- Low-power edge accelerators

Check: task · software · interface

### Server CPUs

Server processors

Select server processors for the CPU platform, socket, core configuration and memory support, while accounting for workload and total system power.

- Single-socket server processors

- Processors for dual- or multi-socket platforms

- High-core-count options

Check: platform · compute · memory

Images illustrate product categories. Some use related equipment or application scenes. They do not identify a specific model, connector, configuration, stock position or supply commitment. Confirm appearance, specifications, condition and delivery terms against the agreed product documentation and order.