-

DDN Inferno Ignites Real-Time AI with 10x Faster Inference Latency

CHATSWORTH, Calif.--(BUSINESS WIRE)--At NVIDIA GTC 2025, DDN, the global leader in AI and data intelligence solutions, is redefining enterprise AI performance with the launch of DDN Inferno, a game-changing inference acceleration appliance that delivers sub-millisecond response times and 10x lower compute costs for real-time AI applications. Inferno is purpose-built to eliminate inference bottlenecks, optimize GPU utilization to 99%, and seamlessly integrate multimodal AI data pipelines.

“Real-time AI isn’t just about speed—it’s about removing every barrier between data and intelligence,” said Omar Orqueda, SVP, Infinia Engineering at DDN. “Inferno delivers the industry’s most advanced inference acceleration."

Share

By combining DDN Infinia with NVIDIA Spectrum-X’s AI-optimized networking, enterprises can accelerate AI workflows, maximize GPU utilization, and scale their AI infrastructure seamlessly.

Unlocking the Next Generation of Real-Time AI

DDN Inferno is designed to tackle two of the biggest challenges in AI inference: latency and cost. By integrating DDN’s high-performance architecture with AI-optimized networking from the largest semiconductor company, Inferno accelerates inference processing in ways never seen before:

  • 10x Lower Latency – Response times now drop to sub-millisecond, ensuring instant AI decision-making in mission-critical environments.
  • 12x Cost-Efficiency Gains – Early testing shows Inferno outperforms AWS S3-based inference stacks by 12x, dramatically reducing compute overhead.
  • 99% GPU Utilization – Inferno removes data bottlenecks, ensuring AI workloads fully leverage GPUs for peak performance.

Powering Enterprise AI Without Limits

With Inferno, enterprises can seamlessly integrate multimodal AI workloads—from language models and computer vision to sensor fusion and real-time analytics. Whether deployed on-premises, in the cloud, or in hybrid environments, Inferno simplifies AI data integration and accelerates inference pipelines.

“Real-time AI isn’t just about speed—it’s about removing every barrier between data and intelligence,” said Omar Orqueda, SVP, Infinia Engineering at DDN. “Inferno delivers the industry’s most advanced inference acceleration, making instant AI a reality while slashing costs at enterprise scale.”

To learn more, please visit ddn.com.

About DDN

DDN is the world’s leading AI and data intelligence company, empowering organizations to maximize the value of their data with end-to-end HPC and AI-focused solutions. Its customers range from the largest global enterprises and AI hyperscalers to cutting-edge research centers, all leveraging DDN’s proven data intelligence platform for scalable, secure, and high-performance AI deployments that drive 10x returns.

Follow DDN: LinkedIn, X, and YouTube.

Contacts

DDN Media Contact:
Amanda Lee
VP, Marketing – Analyst and Media Relations
amlee@ddn.com

DDN


Release Versions

Contacts

DDN Media Contact:
Amanda Lee
VP, Marketing – Analyst and Media Relations
amlee@ddn.com

Social Media Profiles
More News From DDN

DDN Selected to Modernize Research Data Infrastructure at UNSW Sydney

SYDNEY--(BUSINESS WIRE)--DDN, the global leader in AI and data intelligence solutions, today announced that UNSW Sydney has selected DDN to deliver a new research data storage environment as part of the university’s Research Data Experience (RDE) program. Working with Australian software company Arcitecta, DDN will combine its EXAScaler parallel file system with Arcitecta’s Mediaflux® data management platform to help researchers spend less time managing data and more time using it. Following an...

DDN and Nebul Accelerate Sovereign AI Inference with DDN Infinia

BERLIN--(BUSINESS WIRE)--DDN, the global leader in AI and data intelligence solutions, announced today at GTC Berlin 2026 that European AI cloud provider Nebul is using DDN Infinia to accelerate AI inference for sovereign workloads across its NVIDIA-powered infrastructure. Specifically, DDN Infinia is being used to store and reuse key-value (KV) cache, reducing the GPU work required to serve AI models. In testing, DDN helped Nebul sovereign AI workloads find answers faster at a lower cost: Near...

DDN Collaborates with NVIDIA to Advance GPU-Initiated Data Access for Next-Generation AI

SANTA CLARA, Calif.--(BUSINESS WIRE)--DDN, the global leader in AI and data intelligence solutions, today announced a collaboration with NVIDIA within the Storage-Next initiative and focused on helping organizations achieve greater business and financial value from their AI investments. The companies are working together to create a faster, more efficient connection between NVIDIA accelerated computing and the DDN Infinia data intelligence platform. By enabling GPUs to access the data they need...
Back to Newsroom