Adobe is updating its Firefly AI assistant with new chops, and adding it to Premiere, Illustrator, InDesign and Frame.io.

AMD and Rackspace Technology have signed a definitive agreement to deploy an initial 30MW footprint of AMD-based compute capacity across Rackspace’s global data center portfolio. The phased rollout is scheduled to begin in late 2026 and continue through 2028, advancing the memorandum of understanding the companies announced in May.

Under the agreement, AMD becomes a strategic silicon partner within Rackspace’s enterprise AI infrastructure strategy. The deployment will combine AMD Instinct accelerators, including the MI355X, MI350P, and future generations, with AMD EPYC processors to support AI training, inference, and enterprise workloads in regulated industries.

At full deployment, the 30MW environment is expected to provide substantial AI compute capacity for enterprise customers, including organizations in healthcare and other regulated sectors. Rackspace said the infrastructure is designed to support large-scale clinical AI initiatives, inference services, and other workloads that require governance, accountability, and operational oversight.

The companies plan to integrate the AMD hardware stack into Rackspace’s Enterprise AI Cloud architecture. The platform is intended to match workloads with the appropriate compute resources while providing centralized management and operational accountability across the infrastructure stack.

Rackspace CEO Gajen Kandiah said regulated industries require AI infrastructure that is governed end-to-end rather than assembled from multiple independent providers. He positioned the collaboration as an effort to combine compute infrastructure and operating services into a single managed framework with accountability extending from the hardware layer through business outcomes.

AMD Senior Vice President and General Manager of Compute and Enterprise AI Dan McNamara said enterprise AI deployments increasingly require a mix of accelerated and general-purpose computing resources optimized for different workload requirements. He noted that the combination of AMD’s AI compute portfolio and Rackspace’s managed cloud operating model is intended to provide enterprises with scalable and accountable infrastructure for production AI environments.

The agreement also includes joint go-to-market activities. Both companies will dedicate sales and marketing resources and commit personnel to jointly develop and pursue customer opportunities across regulated industries built on AMD-powered infrastructure.

The deployment is expected to accelerate the delivery of the four services outlined in the earlier memorandum of understanding:

• Enterprise AI Cloud
• Enterprise Inference Engine
• Inference as a Service
• Bare Metal AMD Instinct

Together, these offerings are designed to provide a managed AI infrastructure stack spanning bare-metal compute through fully operated inference services. The two companies position the initiative as an alternative to traditional self-managed bare-metal AI deployments, targeting enterprises moving beyond pilot projects and into production AI and agentic workflow implementations within core business systems.

The post AMD and Rackspace Formalize 30MW AI Infrastructure Deployment Across Global Data Centers appeared first on StorageReview.com.

At HPE Discover 2026, HPE announced a broad set of GreenLake enhancements to help enterprises modernize hybrid infrastructure, manage AI operations, and reduce virtualization complexity. The updates span agentic AIOps, private cloud platforms, virtualization alternatives, and software for AI infrastructure management.

The announcements reflect HPE’s continued push to position GreenLake as a unified operating model for hybrid cloud and AI environments, providing centralized operations, governance, and automation across infrastructure, applications, and AI workloads.

“As enterprises scale AI, they need a simpler way to govern AI infrastructure and modernize operations across hybrid environments without fragmentation or unpredictable costs,” said Fidelma Russo, executive vice president, Hybrid Cloud and CTO at HPE. “The latest advancements in GreenLake give enterprises a proven, unified path for agentic hybrid operations today and foundation for future autonomous operations.”

GreenLake Intelligence Adds Agentic AI Operations

At the center of the updates is GreenLake Intelligence, HPE’s agentic AI framework for hybrid cloud and AI operations.

The platform introduces centralized agent management through an agent registry, orchestration capabilities, and governance controls designed to coordinate AI agents across infrastructure, applications, and operational workflows.

HPE is also expanding HPE OpsRamp with a new Operations Copilot that provides visibility into AI agents and large language models. The platform enables organizations to monitor AI utilization, track token consumption, and understand operational costs across AI factories and hybrid infrastructure environments.

Using telemetry correlation and AI-driven root cause analysis, OpsRamp Operations Copilot can proactively identify operational issues and accelerate troubleshooting workflows.

HPE also announced a partnership with ServiceNow to integrate GreenLake Intelligence and OpsRamp observability capabilities into ServiceNow’s AI-driven service management platform. The integration is intended to create a common operational framework spanning infrastructure monitoring and autonomous service delivery.

Morpheus Gains AI-Driven Automation and Centralized Management

HPE continues to position Morpheus as a virtualization and private cloud platform for organizations seeking alternatives to traditional virtualization environments.

The latest release adds HPE Morpheus Orchestration Copilot, a GreenLake Intelligence capability that automates infrastructure and workload provisioning through AI-assisted workflows. The platform supports a bring-your-own-model approach while applying governance and security controls to orchestration processes.

HPE also introduced HPE Morpheus Central, providing centralized governance and management across multiple Morpheus deployments through a single interface.

Several previously announced capabilities are now generally available. Software-defined networking support brings multitenancy, zero-trust security controls, policy enforcement, and VXLAN overlay networking into Morpheus environments while reducing provisioning time by up to 60%.

The platform also now supports intent-based network automation through integration with HPE Juniper Apstra. The capability continuously validates network configurations, detects drift, and automates policy enforcement.

In addition, stretched cluster functionality is now generally available, enabling active-active deployments across two sites with synchronous replication and automated failover for higher availability.

HPE Zerto integration further supports virtualization modernization efforts by enabling live workload migration from VMware environments to HPE virtual machines while maintaining continuous data protection.

New Programs Target Virtualization Migrations

Following announcements at the HPE Partner Growth Summit 2026, HPE is introducing additional programs to accelerate virtualization migrations.

A new platform migration program lets new HPE Morpheus VM Essentials customers receive up to one free year of VM Essentials licenses and a year of HPE Zerto for $1 to support non-disruptive migration to HPE virtual machines, with 0% interest on software financing through HPE Financial Services. The program is intended to reduce migration costs and help organizations avoid double-paying for overlapping virtualization licenses during transitions.

For service providers, HPE introduced HPE CloudOps Software, a platform designed to support the delivery of private cloud services. The software includes multitenancy, self-service provisioning, software-defined networking, policy-based governance, and cost management capabilities.

The offering is paired with HPE’s Cloud Commit model, which provides pricing and service benefits tied to committed spending levels.

Private Cloud Portfolio Gains Air-Gapped Enhancements

HPE also announced updates across its Private Cloud portfolio focused on operational consistency from edge environments through core data centers.

HPE Private Cloud PC3000 now supports standardized air-gapped deployments for disconnected and regulated environments. The platform also adds validation for VMware vSphere 9, enabling customers to stay current with VMware infrastructure while using Morpheus to manage virtual machines and containers through a common control plane.

HPE Private Cloud PC7000 receives similar VMware vSphere 9 validation while incorporating the latest Morpheus capabilities, including Terraform support, infrastructure-as-code workflows, and automated private cloud operations.

For government and highly regulated deployments, the air-gapped version of PC7000 now supports Department of Defense Impact Level 4 (IL4) certification requirements. HPE said the enhancements address secure design, configuration hardening, vulnerability management, and compliance objectives commonly required in sovereign and regulated environments.

GreenLake Flex Expands Hybrid Infrastructure Management

HPE is also updating GreenLake Flex Solutions with additional operational and procurement capabilities.

A new integrated management interface combines infrastructure observability, sustainability metrics, and consumption analytics into a single operational view. The goal is to simplify hybrid infrastructure management while providing better visibility into resource utilization and costs.

HPE also announced that customers can now purchase selected third-party software offerings directly through the GreenLake Marketplace, extending the platform’s ecosystem capabilities.

Combined with GreenLake’s consumption-based pricing model, the updates are intended to give organizations greater flexibility in managing infrastructure investments while supporting modernization initiatives across hybrid cloud and AI environments.

Availability

HPE OpsRamp Operations Copilot within GreenLake Intelligence is available today, as are HPE CloudOps Software for cloud service providers and the GreenLake Marketplace, which supports direct customer-to-ISV transactions.

The latest HPE Morpheus Software updates are rolling out across the second and third quarters of 2026. Air-gapped deployments of HPE Private Cloud PC3000 and PC7000, along with additional Private Cloud capabilities, are expected in the third quarter of 2026.

GreenLake Intelligence and ServiceNow integrations will roll out across 2026 and 2027.

The post HPE Expands GreenLake for Agentic Operations, Private Cloud, and Virtualization Modernization appeared first on StorageReview.com.

Le groupe Caisse des Dépôts, engagé en faveur d’un numérique souverain, responsable et de confiance annonce, avec Numspot, plateforme technologique souveraine et sécurisée, une collaboration stratégique pour un usage maîtrisé des données et des services d’intelligence artificielle.Cette collaboration s’inscrit dans la dynamique portée par Horizon numérique 2030, le plan stratégique du Groupe dédié à l’accélération […]

The post La Caisse des Dépôts S’Engage aux Côtés de Numspot en Faveur d’un Numérique Souverain et Maîtrisé appeared first on StorageNewsletter.

CoreWeave Inc., an essential cloud for AI, announced its bring up of Nvidia Vera Rubin NVL72 on CoreWeave Cloud.Leveraging its purpose-built software and engineering solutions, CoreWeave is the first AI cloud provider to bring up Vera Rubin, extending the CoreWeave platform’s support for Nvidia hardware. The milestone achievement includes the completion of rigorous system-level validation for […]

The post CoreWeave Completes Industry-First Bring-Up and Validation of Nvidia Vera Rubin NVL72 appeared first on StorageNewsletter.

Blog published May 20, 2026 “We started Filebase in 2019 with a simple idea: developers needed better storage infrastructure. Storage should be fast, affordable, easy to integrate, and shouldn’t punish you every time you need to retrieve your own data,” said Joshua here, CEO and co-founder, Filebase. Filebase originally offered S3-compatible storage, then spent the […]

The post Filebase Introduces Fast S3-Compatible Object Storage with Free Egress appeared first on StorageNewsletter.

CoreWeave Inc.,, an essential cloud for AI, announced CoreWeave Sandboxes, an execution layer that gives AI researchers and platform teams secure, isolated environments for running reinforcement learning (RL), agent tool use, and model evaluation.The new offering is available on a customer’s own CoreWeave infrastructure or as a serverless runtime through Weights & Biases (W&B). As […]

The post CoreWeave Sandboxes Launches to Accelerate Reinforcement Learning, Agent Tool Use, and Model Evaluation appeared first on StorageNewsletter.

Unisys has partnered with Rafay Systems, a player in infrastructure orchestration for AI and cloud-native workloads, to help enterprises manage and scale modern cloud and complex end-to-end AI deployments across public, private and hybrid environments.This collaboration combines Unisys’ AI expertise and managed cloud services with Rafay’s self-service platform to help organizations operationalize governed AI with greater […]

The post Unisys and Rafay Systems Partner to Deliver Scalable AI Across Hybrid and Regulated Environments appeared first on StorageNewsletter.

Broadcom has released its Private Cloud Outlook 2026 report, highlighting a significant shift in enterprise AI deployment strategies. According to the survey, organizations are increasingly moving production AI workloads to private cloud environments as concerns about cost, governance, security, and data sovereignty reshape infrastructure planning.

The report suggests the enterprise AI market has moved beyond experimentation, with production deployments driving infrastructure decisions. While the public cloud remains important for AI development and testing, many organizations now prefer the private cloud for large-scale AI inference workloads.

A key finding shows that 56% of enterprises are either running or planning to run production AI inference on private cloud infrastructure. By comparison, only 41% expect to run those workloads in public cloud environments, down from 56% a year earlier. The 15-point decline is among the most significant year-over-year shifts identified in the study.

Broadcom notes that enterprises increasingly associate production AI with higher infrastructure costs, stricter governance requirements, and greater operational complexity. Survey respondents identified data protection and privacy (37%) and security and control (36%) as the top new demands AI is placing on IT organizations.

Cost Pressures Drive Reassessment of Public Cloud

The report also points to growing dissatisfaction with public cloud economics. For the first time since Broadcom began tracking the data, cost has overtaken security as the leading concern associated with public cloud adoption. Thirty-one percent of respondents cited cost as their primary concern, up from 26% in the previous year’s survey.

Nearly all surveyed IT leaders (97%) reported that some portion of their public cloud spending is wasted. More notably, 52% estimated that more than one-quarter of their public cloud budget fails to deliver expected value.

These concerns are driving workload repatriation initiatives. Eighty-three percent of enterprises are evaluating moving workloads from public cloud environments back to private cloud infrastructure, while half of respondents have already completed some level of repatriation.

Security and compliance remain the primary drivers of repatriation efforts, cited by 51% of respondents. Cost predictability and performance followed closely at 39% each, underscoring the growing importance of predictable operating expenses as AI deployments scale.

The report also found that private cloud investment plans continue to outpace public cloud spending. Over a three-year outlook, private cloud spending intent increased by 21 percentage points, compared with a 10-point increase for public cloud spending intent. Additionally, 58% of respondents identified building new workloads on private cloud as a strategic priority, up from 53% a year ago.

Data Sovereignty Becomes a Strategic Priority

Beyond economics, the survey found that geopolitical considerations are increasingly shaping enterprise infrastructure decisions.

Four out of five IT leaders reported that geopolitical developments are shaping IT strategy and operations. For the first time, data sovereignty and residency requirements emerged as the top geopolitical concern, cited by 54% of respondents, surpassing jurisdiction-specific compliance requirements, cited by 51%.

The trend is especially pronounced in highly regulated industries, including financial services, healthcare, life sciences, and the public sector. Organizations in these sectors face mounting pressure to maintain control over sensitive data while complying with increasingly complex cross-border governance requirements.

Broadcom argues that the convergence of AI-driven data growth, regulatory pressures, and cloud cost concerns is strengthening the business case for private cloud infrastructure, enabling organizations to maintain greater control over data location and governance.

Prashanth Shenoy, vice president of marketing for Broadcom’s VMware Cloud Foundation Division, tied the shift directly to the move from pilots to production. “As enterprises move from pilots to running AI at production scale, infrastructure and operational costs spike, security gaps surface, and complexity compounds,” he said. “The research is clear: enterprises increasingly prefer private cloud for production AI.”

Survey Details

The Private Cloud Outlook 2026 report is based on research conducted by Radius Tech in partnership with Broadcom. The survey was fielded between February and March 2026 and included 1,800 senior IT decision-makers from enterprise organizations with at least 1,000 employees across eight countries in North America, Europe, and Asia-Pacific. The report was published in June 2026.

The post Broadcom 2026 Survey: Cost Overtakes Security as Top Public Cloud Concern appeared first on StorageReview.com.

Megaport Ltd., an automated infrastructure platform, announced the launch of Megaport Storage, expanding its platform to deliver integrated compute, network, and storage services.Megaport Storage integrates high-performance, enterprise cloud storage directly into the Megaport Network and Latitude.sh compute platform, giving enterprises a unified foundation that covers the three key pillars of IT infrastructure: compute, network, and […]

The post Megaport Launches Storage, Unifying its Automated Infrastructure Platform Alongside Compute and Network Offerings appeared first on StorageNewsletter.

Lovable and Google signed an expanded multiyear deal that involves a 5x expansion of Lovable's footprint on Google Cloud, and expanded access to Anthropic Claude.

Eon, a cloud backup solutions platform, has launched Eon AI Agent, a tool that lets enterprises query and analyze backup, archive, and production data in plain English without restores, schema reconstruction, or pipeline work. Eon’s cloud backup solutions platform automates backup and recovery across AWS, Microsoft Azure, and Google Cloud, converting static backups into a […]

The post Eon Launches AI Agent for Cloud Backup Solutions that Reduces Data Preparation from Months to Minutes appeared first on StorageNewsletter.

Qumulo announced the Cloud AI Accelerator, a new architecture designed to improve the efficiency of enterprise AI infrastructure by eliminating data movement bottlenecks. The platform presents distributed datasets to GPU resources in real time across regions, clouds, and hybrid environments without requiring replication or staging.

The release builds on a well-documented inefficiency in enterprise AI infrastructure. Citing Cast AI’s 2026 State of Kubernetes Optimization Report, Qumulo points to average enterprise GPU utilization of around 5 percent, with the remaining 95 percent of accelerated compute sitting idle because data must be staged, replicated, and moved into position before workloads can begin. Qumulo CEO Doug Gourlay framed the problem in the announcement: “Every enterprise we talk to is focused on GPU availability, but availability is only half the problem. The deeper issue is utilization, and the culprit is data gravity.”

Rethinking Data Placement for AI Workloads

Traditional approaches to AI infrastructure co-locate storage with GPU clusters, often using high-performance flash systems tightly coupled to compute. While effective during active training or inference, this model does not handle idle periods due to data preparation. It also creates fragmented storage silos as enterprises replicate datasets across environments to keep them close to compute.

Qumulo’s approach shifts the model by decoupling data location from compute location. Instead of moving data to GPUs, the Cloud AI Accelerator enables GPUs to access data in place. This is achieved through a distributed data fabric that provides consistent, real-time access to datasets, regardless of their physical location.

The company frames this capability as enabling “GPU liquidity,” allowing workloads to be scheduled based on available compute capacity rather than data locality constraints. In practice, this enables enterprises to use GPU resources across multiple clouds or regions without pre-positioning data.

Architecture: Data Fabric and Caching Layer

Cloud AI Accelerator is an integration of three Qumulo products that previously shipped separately. Cloud Native Qumulo (CNQ) is Qumulo’s file system that runs natively on AWS, Azure, Google Cloud, and Oracle Cloud Infrastructure. Cloud Data Fabric (CDF), launched in February 2025, provides a central file and object repository with coherent caches at the edge. NeuralCache, added to CDF in April 2025, applies machine learning to predictive read and write caching, and Qumulo claims it reduces GPU data load times by up to 64 percent. Cloud AI Accelerator itself first appeared in November 2025; the May 26 release adds direct connectivity to Microsoft AI Foundry, AWS Bedrock, and Google Vertex AI, formalizes the “GPU liquidity” positioning, and pairs the product with Cisco for hybrid deployments.

The data path runs at the block level from source sites (on-premises clusters, cloud regions, cross-region replicas, or CNQ S3-backed storage) into the Accelerator’s CPU DRAM cache, then directly to the GPUs. The architecture maintains a single source of truth across on-premises, edge, and multi-cloud environments and avoids bulk replication, which reduces both storage overhead and synchronization complexity.

This design also supports integration with managed AI services. Enterprises can connect existing datasets directly to platforms such as Microsoft AI Foundry, AWS Bedrock, and Google Vertex AI without copying data into those environments.

Operational Impact: Reducing Idle Time and Complexity

The primary operational benefit is the elimination of data staging delays. In many AI workflows, data preparation can take days or weeks, delaying model training and reducing effective GPU utilization. By enabling immediate access to datasets, the Cloud AI Accelerator allows workloads to start as soon as compute is available.

This also reduces the need to maintain multiple storage environments. Instead of creating separate data silos for each GPU cluster or cloud region, organizations can operate from a single logical dataset. This simplifies data management and reduces infrastructure sprawl.

From a cost perspective, the model targets idle GPU spend. By eliminating the need to preload data into GPU-attached storage, enterprises can reduce the time GPUs spend waiting for data, improving the overall return on investment for accelerated compute.

Cisco Integration for Hybrid AI Infrastructure

Cisco is the joint go-to-market partner for the hybrid deployment story, with Cisco UCS providing the on-premises compute footprint and Cisco networking and security wrapping the data fabric. Together, Qumulo and Cisco position the offering as infrastructure that adapts in minutes to changing GPU availability, which they argue is what makes GPU liquidity practical at enterprise scale.

The pairing is critical in both directions. It gives Qumulo a validated path into Cisco UCS environments and provides Cisco with a storage answer for hybrid AI customers who want data to stay on-premises while compute scales across hyperscalers. High-throughput, low-latency networking is the load-bearing element here, since data access in place depends on consistent transport between sites.

Availability and Deployment Model

Qumulo Cloud AI Accelerator is now available on AWS, Microsoft Azure, Google Cloud, and Oracle Cloud Infrastructure, with hybrid deployment support in Cisco UCS environments. Qumulo and Cisco will be at Cisco Live 2026 in Las Vegas, at booth #4018, from May 31 through June 4, where the joint offering will be on display.

The release reflects a broader shift in AI infrastructure design toward data-centric architectures. As accelerated compute capacity continues to outpace the infrastructure that feeds it, improving utilization will depend on reducing the time GPUs spend waiting for data. Qumulo’s bet is that making the dataset universally accessible, rather than mobile, is the more durable approach than adding more flash to every GPU cluster.

The post Qumulo and Cisco Pitch GPU Liquidity With Updated Cloud AI Accelerator appeared first on StorageReview.com.

N‑able Inc., a player cybersecurity company delivering business resilience, announced the expansion of Cove Data Protection with a new co-managed Disaster Recovery as a Service (DRaaS) offering.The new capability enables organizations to rapidly recover from cyber incidents and site failures, without the cost, complexity, or risk of building and managing their own disaster recovery environments. […]

The post N-able Accelerates Recovery Time After Critical Events with Disaster Recovery as a Service appeared first on StorageNewsletter.

Druva, a provider of data security, announced a new integration with Dell PowerProtect Data Domain, enabling enterprises to extend their Data Domain environments with SaaS-powered cyber resilience.With this integration, organizations can combine fast local recovery through Data Domain with the simplicity, visibility, and cloud-scale protection of Druva’s fully managed, cloud-native platform.  Enterprises widely trust Dell […]

The post Druva Announces Integration with Dell PowerProtect Data Domain to Modernize Cyber Resilience appeared first on StorageNewsletter.

Summary: HPE Private Cloud now offers Kubernetes management with the latest HPE ProLiant Compute Gen 12, unifying cloud-native and virtualized workloads on a high-performance system HPE Alletra Storage MP X10000 now delivers high-performance file storage, providing file and object on a single platform to simplify data management and accelerate AI data pipelines HPE introduces new […]

The post HPE Delivers Unified Private Clouds and Data Platforms to Accelerate Enterprise Modernization and AI Data Readiness appeared first on StorageNewsletter.

Pinecone, the knowledge infrastructure for AI at scale, announced its expansion into the AWS Europe (Frankfurt) Region (eu-central-1), bringing its full serverless vector database and knowledge infrastructure to central Europe for the first time.The new region enables organizations across Germany, Austria, Switzerland, and the broader European market to run AI workloads with low-latency performance and […]

The post Pinecone Expands in Europe with New Frankfurt Cloud Region, Delivering the Knowledge Infrastructure for AI to Central European Enterprises appeared first on StorageNewsletter.

NVIDIA has started shipping the very first Vera CPUs to major AI firms, marking the official beginning of production to accelerate Agentic AI forward. NVIDIA Vera CPUs, Purpose-Built For Agentic AI, Are Now In Full Production As The Company Hands Out First Chips To Several AI Firms The Vera CPU is the next chapter for NVIDIA's Agentic AI ecosystem, setting the stage for its next multi-billion dollar frontier. Today, NVIDIA's Vice President of Hyperscale and High-Performance Computing, Ian Buck, hand-delivered the first Vera CPUs to four major AI firms who are accelerating Agentic AI forward, these include OpenAI, SpaceX, Anthropic, […]

Read full article at https://wccftech.com/nvidia-hand-delivers-first-vera-cpus-to-anthropic-openai-spacex-oracle-agentic-ai-era/

Cirrascale Cloud Services, an expert neocloud built for Private AI, announced the addition of Tenstorrent Galaxy Blackhole servers to its AI Innovation Cloud.The integration marks Tenstorrent’s entry into broad commercial deployment and expands Cirrascale’s portfolio with hardware built specifically for the demands of real-world AI. Tenstorrent Galaxy is engineered around the metrics that matter most […]

The post Cirrascale Cloud Services Adds Tenstorrent Galaxy Blackhole to Its AI Innovation Cloud appeared first on StorageNewsletter.