DDN announced the launch of DDN Infinia 2.4 at the RAISE Summit in Paris, extending its industry-leading platform for production AI, large-scale inference, and sovereign AI infrastructure.
As AI moves from training models to operating intelligent systems in production, enterprises face a new challenge: maximizing the economic return of AI infrastructure investments. The bottleneck is no longer acquiring GPUs, it is keeping those GPUs productive, reducing cost-per-token, accelerating inference, and securely governing data across multi-tenant AI environments.
Infinia 2.4 establishes the enterprise-grade foundation layer required to run AI factories at scale, combining production-ready multi-tenancy, identity management, governance, and security with the high-performance data architecture that powers some of the world’s largest AI deployments.
By enabling higher GPU utilization, faster data access, improved inference efficiency, and simplified operational management, Infinia helps organizations accelerate time-to-value by 25x, and reduce cost per token by 75%, all while improving the return on billions of dollars invested in AI infrastructure.
“The economics of AI are rapidly becoming more important than the models themselves,” said Alex Bouzari, CEO and Co-Founder at DDN. “The industry has entered an era where success is measured by cost-per-token, inference efficiency, GPU utilization, and business outcomes; not simply the number of GPUs deployed. Organizations need infrastructure that transforms expensive AI investments into productive AI factories. Infinia 2.4 provides the governance, security, performance, and operational foundation required to maximize AI ROI while enabling the next generation of enterprise and sovereign AI.”
Accelerating Inference Economics and Token Efficiency
As enterprises increasingly deploy agentic AI, retrieval-augmented generation (RAG), copilots, and autonomous AI systems, inference has emerged as the dominant operational cost in modern AI environments.
Infinia’s architecture is designed to optimize the economics of production inference through ultra-low-latency data access, high-performance object storage, and intelligent data services that help keep accelerators fully utilized.
DDN continues to lead innovation in AI data infrastructure through capabilities such as:
- High-performance distributed KV cache acceleration that enables 18x faster inference
- Sub-millisecond access to AI datasets and model artifacts
- Massive concurrency for multi-tenant inference environments
- Optimized support for RAG (22x faster than AWS Express), vector databases, agentic AI, and large-scale inference workloads
- Industry-leading GPU utilization up to 99% and reduced infrastructure waste
These capabilities help organizations reduce cost-per-token, improve inference throughput, accelerate response times, and generate greater business value from AI investments.
Introducing the Enterprise Foundation for AI
Infinia 2.4 focuses on four strategic pillars designed to help organizations operationalize AI at scale:
NCP and AI Operator Readiness
The release introduces foundational capabilities required by NCPs, managed AI services operators, and enterprise AI platforms, including:
- Advanced multi-tenancy
- Identity integration and management
- Quota enforcement and governance controls
- Enhanced operational isolation for shared AI environments
These capabilities allow organizations to securely support multiple teams, customers, business units, or sovereign AI workloads from a single platform.
POSIX Support Reaches Limited Availability
Infinia 2.4 delivers the first Limited Availability milestone for POSIX support, including:
- POSIX client qualification on Red Hat Enterprise Linux and Ubuntu
- Defined throughput commitments
- Documented deployment guidance and operational parameters
This milestone expands application flexibility while maintaining Infinia’s high-performance architecture for modern AI and data-intensive workloads.
S3 Compatibility and Continuity
Organizations can adopt Infinia 2.4 without disruption to existing applications and workflows. The release maintains full compatibility with established S3 environments and SDKs while preserving the performance and scalability advantages that enterprises rely on today.
Driving the Future of Enterprise and Sovereign AI
The launch comes as DDN expands its leadership position across hyperscale AI, enterprise AI, inference infrastructure, and sovereign AI initiatives worldwide.
Organizations including NVIDIA, xAI, Salesforce, Mistral, Aleria, SK Telecom, Yotta, TotalEnergies, and leading government and research institutions rely on DDN technology to power some of the world’s largest AI environments, achieving higher infrastructure utilization, faster model deployment, improved inference efficiency, and greater returns on AI investments.
