Scality - Experts & Thought Leaders

Scality, a global pioneer in data infrastructure software for AI storage at scale, announces the availability of Scality AI Inference Factory, an open-code software stack for deploying and operating AI inference on enterprise-owned infrastructure. The solution gives enterprises, government agencies and neo-cloud providers a supported alternative to cloud-based AI services, without having to assemble, integrate and maintain the entire software stack themselves. As AI moves from experimentation into production, organizations are looking for more predictable costs, greater control over model lifecycles and increased data sovereignty. For most organizations, the answer will be hybrid, with the most critical AI processes running on-premises. Running inference locally can address these requirements while keeping sensitive data within infrastructure that organizations own and operate. Inference-serving layer Scality AI Inference Factory brings together validated open-weight models, a disaggregated inference-serving layer, a control plane for authentication, metering, routing and scheduling, and Scality AI Data Infrastructure (ADI), which uses policy-governed autonomous operations to manage massive datasets across the AI lifecycle. Scality validates, ships and maintains the integrated stack. “With AI moving into mission-critical production environments, organizations need greater control over where inference runs, how their models are managed and what happens to their data,” said Jérôme Lecat, CEO at Scality. “For 15 years, Scality has built data infrastructure that thousands of customers around the globe rely on to operate 24/7. AI Inference Factory brings that experience to on-premises AI, giving organizations the reliability and sovereignty they need to run critical AI workloads on their own terms.” Cloud-based inference model Enterprises scaling AI in production are confronting challenges with the cloud-based inference model. With per-token pricing, the more useful an AI workflow becomes, the more it costs, producing bills that are difficult to forecast and impossible to cap. Model versions and quantisation can change at the provider's discretion, affecting the workflows built on them. Organizations with sensitive or regulated data face sovereignty concerns over where their prompts, documents and proprietary code are processed, under which jurisdiction, and who can restrict access to them. Scality AI Inference Factory is designed for organizations that want to run critical AI workloads on infrastructure they control while retaining flexibility across models, hardware and software. The stack supports specialized chatbots, AI-assisted software development, agentic applications and other inference-intensive workloads. High-performance object storage Scality AI Inference Factory combines: Validated open-weight models maintained as part of the supported stack; Disaggregated inference serving that separates prefill from decode so each can scale independently; A control plane that authenticates and meters requests, routes them to the appropriate GPUs holding the relevant context and schedules workloads against SLA targets; and Scality ADI, which provides high-performance object storage for models, enterprise data and inference state. On-premises deployments Scality validates and maintains the complete stack as a supported solution, helping organizations keep pace with rapidly changing models, serving technologies and security requirements without having to integrate and maintain the individual components themselves. "As AI adoption expands and AI agents become more prevalent, organizations are evaluating which IT environments are best suited to run inference. On-premises deployments are coming into focus for a variety of reasons, including cost optimization, data security and privacy, and regulatory requirements. IDC research shows that running inference on-premises is a credible option for a growing set of enterprise and public sector workloads, provided the infrastructure can hold and serve model state efficiently at scale. Scality is among the vendors addressing that requirement across the inference and storage layers," said Nataliya Yezhkova, Vice President, Storage and Data Management, Enterprise Infrastructure, IDC. Reducing inference costs Scality ADI serves as the shared storage layer for AI Inference Factory, extending key-value (KV) cache beyond limited GPU high-bandwidth memory (HBM). This allows inference infrastructure to preserve and retrieve model context instead of requiring GPUs to recompute it, improving GPU utilization and reducing inference costs. This is particularly important for reasoning models and agentic workloads, where KV cache can quickly exceed available GPU memory. Scality ADI provides a shared, multi-petabyte cache that GPUs read at latency the same order of magnitude as GPU memory, allowing them to retrieve existing context and remain focused on inference. Same order of magnitude Scality testing demonstrated that ADI can reduce GPU consumption while maintaining the same level of performance: 1.9-second load time for Gemma-3 27B, almost 10x faster than local NVMe, with the model streamed in parallel across the cluster over RDMA; 166 ms warm time-to-first-token on a 14K-token context restore from ADI, only 83 ms behind HBM; 14x faster KV cache retrieval than recomputation on a 14K-token context and up to 72x faster on a 439K-token context; A KV cache more than 80x larger than a single GPU’s memory, keeping up to 1,000 concurrent sessions resumable without recomputation; No measurable impact on token generation, as context is restored before the first token; and 97% of network line rate for data transfer between GPUs and storage. Same latency targets The architecture separates prefill from decode, with ADI acting as the shared cache between GPU pools. This allows available decode GPUs to access existing context without tying it to a specific GPU server. Separating prefill from decode has documented gains: DistServe (OSDI 2024) measured up to 7.4 times more requests served within the same latency targets. Adding a shared KV cache pool on top, Moonshot AI's Mooncake reported 75 percent more requests on Kimi's production traffic. As Giorgio Regni, Scality CTO, puts it: “The KV cache on Scality ADI is fast enough to sit in the serving path. Restoring a context from ADI is the same order of magnitude as GPU memory, and 14 times faster than recomputing it, with the GPUs staying busy the whole time. Storage is no longer the reason to keep the KV cache inside the GPU server.” AI inference factory Regni continues: “That opens the door to disaggregated serving. One pool of GPUs handles prefill, processing the prompt and writing the KV cache to ADI. A second pool handles decode, reading the cache back and generating tokens. With Scality ADI as the shared cache, any decode GPU can pick up any context, and there is essentially no size limit. Prefill no longer interrupts decode, and both pools run at full load.” For a technical deep dive into the AI Inference Factory architecture and test results, visit Scality’s companion blog. Sovereign AI workloads Scality AI Inference Factory is designed to preserve customer choice across the AI infrastructure stack. It is compatible with open-source harnesses and agentic frameworks such as OpenCode, Hermes, Goose, LangGraph and Pydantic AI, and runs validated open-weight models such as Mistral, Gemma, gpt-oss, Qwen, Kimi, GLM, and DeepSeek. The software deploys on standard servers from Dell, HPE, Lenovo and Supermicro. Every software component Scality ships is delivered as open code, enabling customers to inspect how inference state is stored and moved, and to submit contributions for Scality review. For organizations running sensitive, regulated or sovereign AI workloads, this provides transparency into the software handling their models and data rather than requiring them to rely on a closed external service. Scality ADI integrates with standard AI stacks and deploys at multi-petabyte scale on NVMe, with RDMA access to HDD for virtually unlimited KV cache capacity. A single namespace automatically tiers data across TLC, HDD and, optionally, tape, allowing organizations to align storage performance and economics with different stages of the AI data lifecycle. Scality AI Inference Factory is available now as a software license or as a fully managed service.

As cloud and managed service providers race to deliver backup-as-a-service (BaaS) at scale, a critical operational challenge has emerged: managing tens to hundreds of individual object storage deployments spread across customer sites, each requiring monitoring, maintenance, and billing reconciliation. Scality, a pioneer in data infrastructure software for AI-era storage at scale, today announced general availability of Scality Maestro, a fleet management platform purpose-built for service providers operating large numbers of Scality ARTESCA object storage deployments on behalf of their customers. Managing single deployment Managing distributed object storage infrastructure at scale is fundamentally different from managing a single deployment. Service providers need a single pane of glass to monitor health, push firmware and software updates, track capacity utilization across all customer sites, and do so without requiring VPN tunnels into every customer environment. As BaaS offerings grow from dozens to hundreds of sites, this operational gap becomes a hard constraint on scalability. Co-developed with cloud and service provider partners (SCSP), Scality Maestro is now in production use across customer deployments and provides service providers with: Centralized health monitoring and alerting across the entire Scality ARTESCA fleet End-to-end management down to the hardware layer, including ARTESCA software upgrades and server firmware updates Aggregated capacity utilization data across all customer deployments, enabling automated pay-as-you-go billing Out-of-band connectivity architecture that eliminates VPN requirements, as all traffic flows from ARTESCA to Maestro, never the reverse Support for enterprises managing ARTESCA across branch offices or distributed edge locations Data protection architecture "We manage multiple Scality ARTESCA deployments across our key customer sites in the UK and Ireland as part of our backup-as-a-service offering, and until Maestro, every one of them was independently managed - separate logins, VPN tunnels, manual update cycles, and monthly capacity reports assembled by hand. Instead, Maestro gives us a single view of the entire fleet. Software updates that consume hours of staff time can now be monitored centrally, and we can grow the fleet without adding operational headcount. We can already foresee a significant difference in running our service," said Dominic McLouglin, CEO Autodata. While Maestro was designed primarily for the SCSP and MSP market, the platform is equally well suited to enterprise organizations running ARTESCA across multiple locations, whether at the edge, in branch offices, or as part of a distributed data protection architecture. Operational inflection point Once deployments expand beyond a handful of sites, organizations reach an operational inflection point: tools that work well for a single site cannot efficiently manage tens or hundreds. Maestro provides the centralized management needed to operate at that scale. “Service providers building BaaS businesses on Scality ARTESCA are managing infrastructure at a scale that demands enterprise-grade operational tooling. Maestro was built with our SCSP partners to solve the real operational problems they face every day with centralized visibility, automated management, and the billing infrastructure to run a sustainable managed service. The fact that it requires no VPN and no network reconfiguration on the customer side was a hard requirement from day one,” said Thomas Danan, Sr. Product Director, Scality. Scality Maestro 1.1 is generally available and supports all Scality ARTESCA deployments running version 4.0.3 or later. It is currently available as an on-premises deployment, with a SaaS delivery model planned for future release. For Scality service providers, full documentation is available at documentation.scality.com.

Scality, a global pioneer in data infrastructure software for the AI era, and WEKA, the data and memory infrastructure company, announces an expanded partnership in France, anchored by a new joint customer support agreement. Under the agreement, Scality will distribute the companies’ joint solution to customers in France, giving local enterprises a single, in-country point of contact for sales and tier-one support. The announcement precedes RAISE Summit 2026, Europe’s premier AI event, taking place July 8–9 at the Carrousel du Louvre in Paris, where both companies are exhibiting. Delivering autonomous operations Scality and WEKA’s combined technologies deliver a complementary solution for AI workloads. WEKA’s NeuralMesh software provides accelerated storage and context memory performance at scale, keeping GPUs fully utilised for AI model training and inference. Scality ADI (Autonomous Data Infrastructure) is a data infrastructure platform that delivers autonomous operations, cyber resilience, and sovereign control across the full data lifecycle, from active workloads to durable, long-term retention at exabyte scale. The new agreement makes the combined solution easier for French customers to adopt and operate, with front-line technical support delivered locally by Scality. Jointly validated solution The support agreement builds on the jointly validated solution the two companies announced on February 24, 2026, which pairs WEKA’s NeuralMesh high-performance AI storage and context memory platform with a cost-efficient Scality RING object tier. The integration uses Scality’s lightweight object connector for NeuralMesh, delivering up to 10x faster performance and up to 20% lower infrastructure costs in Scality testing. It also reflects a broader expansion of joint go-to-market activities in France, where Scality and WEKA are engaging a growing set of shared prospects. By aligning their complementary technologies and now their local support and sales motions, the partners aim to give French enterprises, government organizations, and AI builders a clear, low-risk path to high-performance, cost-efficient, cyber-resilient AI infrastructure. Mission-critical environments Both companies are exhibiting at RAISE Summit 2026. Visit Scality at booth #3D and WEKA at booth #2D to learn more about the joint solution and meet the experts behind it. The companies will co-host an invitation-only Lumiere Candlelight® concert and dinner at the Pullman Paris Tour Eiffel on Wednesday, July 8, bringing together Europe’s top AI builders, founders, and partners beyond the conference floor. “The race for AI is no longer limited by GPUs. It’s increasingly limited by data infrastructure. Our partnership with WEKA brings those strengths together, and extending it with local, French-language support means our joint customers in France get the combined solution backed by a single, in-country point of contact. This is exactly the kind of practical, customer-first collaboration that earns trust in mission-critical environments,” said Jérôme Lecat, CEO of Scality. "AI doesn't stall because enterprises run out of models. It stalls because infrastructure can't keep pace with the demand they create. NeuralMesh solves the performance layer: it maximises GPU utilization, scales inference throughput, and drives down cost per token. Scality covers the full data lifecycle with the cyber resilience and sovereign controls that regulated European industries require. Local French-language support from Scality removes the final barrier to adoption. For French enterprises deploying at scale, that is a meaningfully shorter, lower-risk path to production," said Nilesh Patel, Chief Strategy Officer of WEKA.