---
title: "NVIDIA BlueField-4 Powers New Scale-In Network Infrastructure for Agentic AI Factories"
description: "Agentic AI factories connect diverse users, agents, applications, data sources, and storage systems to massively accelerated compute, making dedicated DPU processing essential for line-rate networking, storage, and security. Scale-In evolves north-south access into a coordinated infrastructure domain built with BlueField-4, NVIDIA DOCA, and Spectrum-X Ethernet. BlueField-4 combines programmable control-plane processing with inline data-path engines, a 64-core Grace CPU, LPDDR5X memory, PCIe Gen6 host connectivity, and an 800 Gb/s network interface. The architecture offloads security, tenant isolation, storage protocols, provisioning, and telemetry from host CPUs; the source states that Spectrum-X storage paths can provide up to 1.45x the throughput of off-the-shelf Ethernet, while independent control and observability support more consistent operations as AI infrastructure scales."
---

# NVIDIA BlueField-4 Powers New Scale-In Network Infrastructure for Agentic AI Factories

[NVIDIA](https://yomu.fyi/company/nvidia-developer-blog) · Michelle Horton · Aug 24, 2026

**Type:** Explainer

## Summary

Agentic AI factories connect diverse users, agents, applications, data sources, and storage systems to massively accelerated compute, making dedicated DPU processing essential for line-rate networking, storage, and security. Scale-In evolves north-south access into a coordinated infrastructure domain built with BlueField-4, NVIDIA DOCA, and Spectrum-X Ethernet. BlueField-4 combines programmable control-plane processing with inline data-path engines, a 64-core Grace CPU, LPDDR5X memory, PCIe Gen6 host connectivity, and an 800 Gb/s network interface. The architecture offloads security, tenant isolation, storage protocols, provisioning, and telemetry from host CPUs; the source states that Spectrum-X storage paths can provide up to 1.45x the throughput of off-the-shelf Ethernet, while independent control and observability support more consistent operations as AI infrastructure scales.

## Context

Traditional cloud infrastructure was designed for predictable, general-purpose workloads and standard interfaces, while agentic AI factories continuously connect diverse users, agents, applications, enterprise data sources, and storage systems to massively accelerated compute. The source states that software-defined networking, composability, and elasticity remain essential but are no longer sufficient, and that infrastructure services cannot rely solely on software running on general-purpose host CPUs.

## Approach / What changed

Scale-In unifies and accelerates access, security, data movement, provisioning, and observability across the AI factory. BlueField-4 provides host-independent infrastructure processing and offload, NVIDIA DOCA supplies programming and orchestration frameworks, and Spectrum-X Ethernet provides high-performance connectivity and performance isolation. BlueField-4 uses control-plane software and inline engines for local policy enforcement, while DOCA services support Kubernetes-native provisioning and telemetry.

## Takeaways

- BlueField-4 keeps infrastructure processing outside tenant hosts, allowing security policies, service state, and telemetry to be managed without relying on host CPUs or consuming their resources.
- BlueField-4 accelerates NVMe-oF, file and object storage protocols over RDMA and TCP, storage virtualization, and data movement; the source reports up to 1.45x more storage throughput than off-the-shelf Ethernet with Spectrum-X.
- DOCA Platform Framework provisions, manages, and scales BlueField DPUs as Kubernetes nodes, while DOCA Telemetry exports infrastructure signals for monitoring network traffic, storage access, service health, and utilization.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Kubernetes](https://yomu.fyi/topic/kubernetes), [Observability](https://yomu.fyi/topic/observability), [Performance](https://yomu.fyi/topic/performance), [Scalability](https://yomu.fyi/topic/scalability)

- Source: [NVIDIA](https://developer.nvidia.com/blog/nvidia-bluefield-4-powers-new-scale-in-network-infrastructure-for-agentic-ai-factories)
- Source URL: https://developer.nvidia.com/blog/nvidia-bluefield-4-powers-new-scale-in-network-infrastructure-for-agentic-ai-factories
- Ingested by Yomu: 2026-08-29T01:38:32.662Z

[Read original post](https://developer.nvidia.com/blog/nvidia-bluefield-4-powers-new-scale-in-network-infrastructure-for-agentic-ai-factories)