The platform’s revolutionary design marks a major evolution in AI infrastructure, eliminating traditional CPU requirements while delivering breakthrough performance density, linear scalability and exceptional power efficiency for enterprise AI factories.
WASHINGTON and CAMPBELL, California., October 29, 2025 /PRNewswire/ — From GTC Washington, DC 2025: WEKA announced today that it is developing the next generation of NeuralMesh™ by WEKA®, its intelligent storage system, for the new NVIDIA BlueField-4 Data Processing Unit (DPU)marking a transformational shift in how AI infrastructure will be architected and deployed. This revolutionary approach eliminates the need for standalone CPU servers, instead leveraging the unprecedented 800 Gbps network bandwidth and 6x compute improvement of NVIDIA BlueField-4 to provide what WEKA CEO Liran Zvibel calls “the perfect foundation for the future of AI data infrastructure.”
Reinventing AI infrastructure architecture
Rather than deploy Neural mesh on traditional servers with separate processors, the next generation of WEKA’s NeuralMesh storage software will run directly on NVIDIA BlueField-4, fundamentally simplifying the deployment of AI infrastructure while significantly improving economics, performance and power efficiency. This architectural change represents WEKA’s most substantial alignment to date with NVIDIA’s infrastructure roadmap and vision for the AI data center.
The perfect complement to modern AI infrastructure
NVIDIA BlueField-4 brings programmable infrastructure, acceleration, Zero Trust security, and massive networking capabilities that perfectly align with NeuralMesh’s microservices-based mesh architecture. When combined with NVIDIA’s latest accelerated computing platforms, BlueField-4 and NeuralMesh create a unified and efficient foundation for large-scale AI factories.
“The rapid evolution of AI requires intelligent data infrastructure that can adapt and scale with unprecedented efficiency,” said Liran Zvibel, co-founder and CEO of WEKA. “WEKA’s NeuralMesh architecture, designed for NVIDIA BlueField-4, is a tremendous step forward in providing the foundational storage for next-generation AI factories.
“The demands of AI reasoning and other inference workloads require a new foundation for data infrastructure – one that unifies compute, networking, and storage for unprecedented efficiency and scalability,” said Justin Boitano, vice president of enterprise products at NVIDIA. “With the integration of NVIDIA BlueField-4, WEKA’s NeuralMesh storage system supports this architectural transformation to power efficient data processing in large-scale AI factories.
Advantages of BlueField-4 based architecture
WEKA’s next-generation NeuralMesh storage system, built on BlueField-4, will offer:
-
Exceptional energy efficiency: Delivers over 100x token/watt improvement for agentic AI workflows
-
Simplified infrastructure: Eliminates the need for dedicated storage servers with standalone processors, reducing complexity and footprint.
-
Superior Economy: Significantly reduces infrastructure costs by consolidating compute, networking, and storage functions.
-
Improved performance: Leverages BlueField-4’s 800 Gbps network and 6x compute enhancement for unparalleled data movement speeds.
-
Seamless integration: Aligns with NVIDIA’s infrastructure roadmap and AI factory architectures.
- Zero trust security: Acceleration of integrated security and isolation of tenants at the line rate via the NVIDIA DOCA™ Software Framework.
A collaboration for the age of reasoning
WEKA and NVIDIA have worked closely together for nearly a decade, extending NVIDIA AI Enterprise SoftwareWEKA obtaining several NVIDIA certifications and collaborating on the introduction of new NVIDIA technologies. NeuralMesh storage software built on BlueField-4 represents WEKA’s deepest integration of NVIDIA technologies ever.
“Energy efficiency is key to bringing AI factories online at scale. NVIDIA BlueField-4 and WEKA’s NeuralMesh storage software will directly address this challenge, delivering revolutionary token-per-watt efficiency without compromising performance, scalability, or operational simplicity. We view the integration of NeuralMesh with BlueField-4 as a strategic growth engine that can simplify and accelerate enterprise AI factory deployments for our customers,” said Nilesh Patel, Chief Strategy Officer at WEKA.
Availability and next steps
WEKA is actively developing its next-generation NeuralMesh software release for NVIDIA BlueField-4, with detailed roadmap information to be shared with customers and partners in early 2026. Organizations interested in learning more about WEKA’s NeuralMesh architecture can contact WEKA directly or visit www.weka.io.
About WEKA
WEKA transforms the way organizations create, run and scale AI workflows with NeuralMesh™ by WEKA®, its intelligent and adaptive mesh storage system. Unlike traditional data infrastructure, which becomes slower and more fragile as workloads increase, NeuralMesh becomes faster, stronger and more efficient as it scales, growing dynamically with AI environments to provide a flexible foundation for enterprise AI and agentic AI innovation. Trusted by 30% of Fortune 50 companies, NeuralMesh helps large enterprises, AI cloud providers, and AI creators optimize their GPUs, scale AI faster, and reduce their innovation costs. Learn more about www.weka.io or connect with us on LinkedIn And X.
WEKA and the W logo are registered trademarks of WekaIO, Inc. Other trade names mentioned may be trademarks of their respective owners.
Show original content:https://www.prnewswire.com/apac/news-releases/weka-announces-new-neuralmesh-architecture-built-for-nvidia-bluefield-4-302596949.html
SOURCE SET
