R&D results confirm industry-first commercial distributed GPU supercluster architecture; commercial launch targeted for Q3 2026
NEW YORK, July 9, 2026 /PRNewswire/ -- WhiteFiber, Inc. (NASDAQ: WYFI), a leading provider of AI infrastructure solutions, today announced initial R&D testing results forit's cross-data-center networking solution, a proprietary distributed GPU supercluster architecture. Initial testing achieved 111.2 Tbps across 83km of dark fiber, already roughly double the capacity of comparable published full-spectrum field trials, using only a portion of available fiber spectrum. Guaranteed round-trip latency of 0.9ms sits within 8% of the physical limit for light in fiber over that distance. Full-fiber lighting testing is planned prior to commercial launch in Q3 2026.
The cross-data-center networking solution links two geographically separated data centers into a single logical GPU supercluster operating as one unified system, not two connected environments. The architecture enables enterprises to run AI workloads that exceed the scale, resilience, and compliance capabilities of any single facility. WhiteFiber has submitted patent applications for the underlying implementation.
While the distributed architecture was used for R&D and demonstration, this technology has applications beyond this use case, including telecommunications, edge computing, and sovereign AI.
It was built in collaboration with DriveNets, which provides the high-performance network fabric connecting both sites, and WEKA NeuralMesh, which provides high-performance data and memory infrastructure across the cluster.
"These results validate what we set out to prove: that geographic distance does not have to be a constraint on AI infrastructure," said Sam Tabar, Chief Executive Officer of WhiteFiber. "This is the foundation for a new class of AI compute, one that delivers the performance of a single supercluster with the resilience and flexibility of a distributed system. We are excited to bring this capability to market."
"Achieving 111.2 Tbps with sub-millisecond latency across 83 kilometers is the result of months of precise, disciplined engineering," said Tobias Ford, Principal Design Engineer at WhiteFiber. "Every element of this system was designed and validated to perform at this level."
"WhiteFiber's distributed cluster technology has the potential to reshape how AI infrastructure is deployed. WEKA is proud to support this project as WhiteFiber's AI infrastructure partner. Together, we are helping deliver a full-stack solution designed to give customers ultra-low latency, flexibility, and resilience at scale," said Liran Zvibel, Co-founder & CEO at WEKA.
"What WhiteFiber has built demonstrates what becomes possible when you pair the right networking architecture with genuine engineering ambition," said Yossi Kikozashvili, VP Product Management, AI at DriveNets. "Our Ethernet-based fabric supports the highest performance in the most demanding, high-bandwidth, low-latency environments, ensuring optimized utilization of GPU and power resources in a scale-across supercluster architecture. These results are a direct reflection of that."
WhiteFiber will share additional details about availability, architectural design, and pricing in conjunction with the Q3 2026 commercial launch. To learn more about the cross-data-center networking solution, visit whitefiber.com/distributed-cluster-networking.
About DriveNets
DriveNets is a leader in large-scale networking solutions for AI infrastructure and service providers. The company pioneered a disaggregated networking architecture that transforms the economics of large-scale networks while maximizing performance, utilization, and operational efficiency. Its high-performance AI fabric maximizes XPU utilization and accelerates deployments by optimizing the AI stack end-to-end, resulting in higher tokens-per-second and lower cost-per-token. DriveNets' solutions power production networks for global tier-1 operators like AT&T and Comcast, and scale multi-vendor AI infrastructures at foundation model labs, NeoClouds, and enterprises. Learn more at https://www.drivenets.com.
About WEKA
WEKA is the AI data and memory infrastructure company transforming the economics of agentic AI. Its NeuralMesh™ platform unifies high-performance data storage with extended GPU memory, giving enterprises, AI cloud providers, and AI builders a single foundation for training, inference, and agentic workloads. With Augmented Memory Grid, NeuralMesh extends GPU memory capacity by 1000x, accelerates time to first token by up to 20x, and delivers 10x more concurrent users from the same GPU footprint, proven in production benchmarks. Trusted by 30% of the Fortune 50, WEKA enables organizations to scale AI faster, optimize GPU utilization, and reduce the cost of every token served. Learn more at www.weka.io or connect with us on LinkedIn and X.
About WhiteFiber, Inc.
WhiteFiber is a leading provider of artificial intelligence ("AI") infrastructure solutions. WhiteFiber owns high-performance computing data centers and provides cloud services to customers. Our vertically integrated model combines specialized colocation, hosting, and cloud services engineered to maximize performance, efficiency, and margin for generative AI workloads. For more information, visit www.whitefiber.com. Follow us on LinkedIn and X @WhiteFiber_.
Forward-Looking Statements
This press release may contain forward-looking statements within the meaning of applicable securities laws. These statements are based on current expectations and involve risks and uncertainties that may cause actual results to differ materially. WhiteFiber undertakes no obligation to update any forward-looking statements except as required by law. All forward-looking statements speak only as of the date of this press release.
Forward-looking statements in this press release include, without limitation: the anticipated commercial launch of this solution Project Redwood in Q3 2026; the planned completion of full-fiber spectrum testing prior to such launch; the anticipated disclosure of additional details regarding availability, architectural design, and pricing in conjunction with the Q3 2026 launch; the expected commercial applications of the Project Redwood architecture, including in telecommunications, edge computing, and sovereign AI; the potential of the Company's distributed GPU supercluster architecture to enable AI workloads that exceed the scale, resilience, and compliance capabilities of any single facility; and the pending patent applications relating to the underlying implementation and any protection they may afford. These forward-looking statements are based on management's current expectations and beliefs as of the date of this press release and are subject to a number of risks, uncertainties, and assumptions that could cause actual results to differ materially from those described in the forward-looking statements. Such risks and uncertainties include, but are not limited to: the Company's ability to successfully complete full-fiber spectrum testing and meet the Q3 2026 commercial launch timeline; technical, engineering, or infrastructure challenges that may delay or prevent commercialization of the Project Redwood architecture; the ability of the Company and its partners, DriveNets and WEKA, to maintain and scale the collaborative relationship necessary to deliver the integrated solution described herein; the outcome of the Company's pending patent applications and the risk that such applications may not result in issued patents or may not provide meaningful intellectual property protection; general economic conditions, capital market conditions, and fluctuations in demand for AI infrastructure and cloud services; regulatory, export control, or data sovereignty requirements that may affect the Company's ability to deploy or commercialize its technology in certain markets; and other risks and uncertainties described from time to time in the Company's filings with the Securities and Exchange Commission, including the Company's most recent Annual Report on Form 10-K and any subsequent Quarterly Reports on Form 10-Q.
Investor Contact
WhiteFiber
IR@whitefiber.com
Media Contact
Michael Francisco
michael@whitefiber.com
View original content to download multimedia:https://www.prnewswire.com/news-releases/whitefiber-announces-cross-data-center-ai-infrastructure-innovation-delivering-111-2-tbps-bandwidth-with-sub-millisecond-latency-across-83km-302821368.html
SOURCE WhiteFiber, Inc.
