SC25: Pliops and DapuStor Join Forces to Advance AI and Data Acceleration

Pliops announced a collaboration with DapuStor Corp. to integrate its high-performance SSDs into Pliops’ LightningAI KV-Cache offloading solution.

This partnership strengthens Pliops’ ecosystem and reinforces its commitment to delivering high-performance, scalable solutions for AI and data-intensive workloads.

Early enterprise deployments of the integrated solution have demonstrated enhanced performance and efficiency, providing measurable value to customers. By combining the company’s KV-Cache offload acceleration technology with DapuStor’s enterprise-grade SSDs, the collaboration delivers a powerful, reliable, and scalable solution for AI and data applications. DapuStor’s strong APAC market presence, along with its capable sales and support teams, further amplifies the partnership’s impact – enabling faster adoption and improved time-to-value for customers globally. In parallel, the XDP LightningAI Accelerator card has been successfully validated with DapuStor R6101 NVMe SSDs.

“This validation underscores DapuStor’s commitment to delivering high-performance storage solutions that perfectly complement cutting-edge accelerated AI workloads,” said Alfred Chase Hui, VP, international business, DapuStor. “The rigorous testing between DapuStor NVMe SSDs and the Pliops LightningAI solution proves their reliability and efficiency in enterprise-grade AI inference environments, such as the vLLM architecture.”

As part of this validation, Pliops tested its accelerated vLLM inference architecture using the LightningAI framework, leveraging the Llama-3.1-8B-Instruct model and the vLLM multi-turn benchmark. The results confirmed full compatibility and readiness of the Pliops XDP solution with DapuStor SSDs for AI and inference workloads.

“This collaboration reflects our continued focus on ecosystem collaboration and delivering real-world value to our customers,” said Ido Bukspan, CEO, Pliops. “By working closely with partners like DapuStor, we’re enabling next-generation infrastructure that meets the demands of modern AI and data workloads.”

Live SC25 Demos Highlight Performance Gains
At SC25 (booth #4608), Pliops will host live demos and ‘Memory Minutes’ – bite-sized sessions that highlight LightningAI’s architecture, deployment success stories, and roadmap for emerging workloads. The demos will feature solutions optimized for both NVIDIA and AMD GPUs, underscoring LightningAI’s flexibility and performance across diverse compute environments.

Resources:
LightningAI Solution Brief   
DapuStor R6101 NVMe SSDs DS