en.Wedoany.com Reported - July 7, 2026, Paris – DDN announced the launch of DDN Infinia 2.4 at the RAISE Summit, expanding its platform for production AI, large-scale inference, and sovereign AI infrastructure.
Enterprise AI applications are shifting from model training to running intelligent systems in production environments, facing the challenge of improving return on AI infrastructure investments. The bottleneck is no longer limited to acquiring GPUs, but lies in keeping GPUs efficiently utilized, reducing per-token costs, accelerating inference, and securely managing data in multi-tenant AI environments.
Infinia 2.4 combines enterprise-grade features such as production-level multi-tenancy, identity management, governance, and security with a high-performance data architecture that supports large-scale global AI deployments. This release aims to establish the foundation needed to run AI factories at scale, supporting NVIDIA DSX-based AI factory deployments by improving GPU utilization, accelerating data access, enhancing inference efficiency, and simplifying operational management, helping organizations increase the return on their AI infrastructure investments.
DDN CEO and Co-Founder Alex Bouzari stated that the industry has entered an era where success is measured by per-token cost, inference efficiency, GPU utilization, and business outcomes. Organizations need infrastructure that can transform AI investments into efficient AI factories. Infinia 2.4 provides the governance, security, performance, and operational foundation to support next-generation enterprise and sovereign AI.
As enterprises deploy agentic AI, retrieval-augmented generation (RAG), copilots, and autonomous AI systems, inference has become the primary operational cost in modern AI environments. The Infinia architecture optimizes the economics of production inference through ultra-low-latency data access, high-performance object storage, and intelligent data services. Its core capabilities include high-performance distributed KV cache acceleration, sub-millisecond access to AI datasets and model artifacts, massive concurrency for multi-tenant inference environments, and optimized support for RAG, vector databases, agentic AI, and large-scale inference workloads, all of which help reduce per-token costs, improve inference throughput, and minimize infrastructure waste.
Infinia 2.4 focuses on four strategic pillars to help organizations operate AI at scale. In terms of AI Cloud Partner and Operator Readiness, this release introduces advanced multi-tenancy, identity integration and management, quota enforcement and governance controls, and enhanced operational isolation for shared AI environments, allowing organizations to securely support multiple teams or workloads from a single platform. Regarding POSIX support, Infinia 2.4 achieves its first limited availability milestone, including client authentication on Red Hat Enterprise Linux and Ubuntu, clear throughput commitments, and documented deployment guidance. For S3 compatibility, this release maintains full compatibility with existing S3 environments and SDKs, ensuring organizations can adopt the new version without disrupting existing applications and workflows.
DDN's data intelligence platform provides exabyte-scale proven data intelligence across millions of GPUs, supporting organizations including NVIDIA, xAI, Salesforce, Mistral, SK Telecom, Yotta, as well as government and research institutions in running large-scale AI environments, aiming to achieve higher infrastructure utilization and model deployment efficiency. At the RAISE Summit, DDN executives will discuss the evolution of AI infrastructure and the role of data intelligence in supporting enterprise and sovereign AI initiatives.
