Wiwynn Corporation

Best verified results on Llama 2 70B LoRA using 1x and 8x NVIDIA GB200 NVL72 systems, production-deployed to power APAC AI training at YTL.

TAIPEI, Nov. 17, 2025 /PRNewswire/ -- Wiwynn announced best results in the MLPerf® Training v5.1 Llama 2 70B LoRA benchmark (Closed division), earning best performance on both 1x and 8x NVIDIA GB200 NVL72 configurations. The submissions were executed on production systems already deployed by YTL AI Cloud, spanning a 1-rack NVIDIA GB200 NVL72 (with 72 NVIDIA Blackwell GPUs) and an 8-rack NVIDIA GB200 NVL72 integrating 576 GPUs—demonstrating leadership from single-rack to multi-rack scale.

The verified MLPerf scores highlight Wiwynn's strengths in system design, manufacturing, liquid cooling, multi-rack integration, and hardware/software co-optimization, combined with YTL's excellence in AI infrastructure integration and operations. Together, the partners demonstrate how close collaboration between system manufacturers and data center operators can deliver production-grade, benchmark-verified AI training performance.

 "Wiwynn designs for workload optimization and real-world deployment," said William Lin, President and CEO at Wiwynn. "Our collaboration with YTL spans from L11 system integration to L12, delivering expanded infrastructure and software integration. Our solution built on NVIDIA GB200 NVL72 infrastructure at YTL shows how system engineering and software tuning unlock the full potential of large-scale GPU clusters."

"At YTL AI Cloud, we are building the region's most advanced AI infrastructure to serve as a premium hub for AI training and inferencing across APAC," said Philip Lin, CEO, YTL AI Cloud. "Our collaboration with Wiwynn demonstrates how the right facility design, infrastructure readiness, and system partnership can deliver world-class AI capability at production scale."

"Congratulations to Wiwynn on their strong achievements in MLPerf® Training v5.1. We appreciate their active, transparent participation and knowledge sharing, which strengthen the ecosystem and supports our mission of open collaboration to improve AI systems' accuracy, safety, speed, and efficiency," said David Kanter, Founder and Head of MLPerf, MLCommons.

YTL AI Cloud's large scale clusters are purpose built with the most advanced GPUs, liquid-cooled high-density racks, redundant power architecture, and low-latency interconnects. As a strategic AI hub for the Asia-Pacific region, YTL AI Cloud in Johor, Malaysia enables global and regional customers to deploy, train, and scale frontier AI models such as Llama 2 70B efficiently and sustainably.

By combining Wiwynn's cutting-edge system integration with YTL's robust AI data center foundation, the collaboration establishes a new standard for high-performance, scalable, and sustainable AI training infrastructure in the region.

About Wiwynn

Wiwynn is an innovative cloud IT infrastructure provider of high-quality computing and storage products, plus rack solutions for leading data centers. We are committed to the vision of "unleash the power of digitalization; ignite the innovation of sustainability". The company aggressively invests in next-generation technologies to provide the best TCO (Total Cost of Ownership), workload, and energy-optimized IT solutions from cloud to edge.

For more information, please visit Wiwynn website, Facebook, and Linkedin.

View original content to download multimedia:https://www.prnewswire.com/news-releases/wiwynn-delivers-best-mlperf-training-v5-1-closed-llama-2-70b-lora-results-at-ytl-malaysia-data-center-302616715.html

SOURCE Wiwynn

SAN JOSE, Calif., Oct. 13, 2025 /PRNewswire/ -- Wiwynn (6669), an innovative cloud IT infrastructure provider for data centers, unveiled its double-wide rack architecture to address the industry shift toward larger, higher‑power AI chips at the OCP Global Summit 2025 (Booth B13, San Jose Convention Center).

The architecture brings together an HVDC power rack and busbar, advanced liquid cooling, and a signal‑integrity‑optimized compute/switch layout to tackle data transmission, power delivery, thermal, and mechanical challenges in high‑density computing—propelling the future of AI and turning ideas into impact.

Key innovations on display

• Double-Wide Rack: Doubles the width of traditional rack to accommodate growing chip/module footprints as compute demand rises. The double‑wide compute tray places four large AI accelerators side by side, supporting chips scaling to 9.5‑reticle with 12× HBM and substrates up to 120 × 150 mm. The design preserves on‑board high‑speed interconnects and signal integrity while reducing cable routing and signal loss. It is co‑designed with the switch tray configuration to ensure high‑speed signal quality in scale‑up scenarios. The compute and switch trays use an advanced mechanical design with a reinforced chassis to prevent sagging.
  
  The new architecture is engineered to accommodate next-generation accelerators such as AMD Instinct™ MI400 Series GPUs, enabling rack scale performance for frontier AI training and inference.
• HVDC power: To meet surging rack‑level power density, the architecture adopts HVDC power delivery. A HVDC power rack converts AC to ±400/800 VDC and distributes it to IT racks next to it via vertical and horizontal busbars and connectors, significantly reducing distribution losses while boosting energy efficiency and scalability. With ecosystem partners, Wiwynn offers ±400/800 VDC and 50 VDC busbar options and the required power delivery boards (PDBs) to flexibly support data center needs.
• Liquid‑cooled Busbar: Engineered for high‑current busbars, integrating liquid cooling to control temperature and reliability, improving safety and stability. Supports Wiwynn's in-house design with flexible inlet/outlet configurations to fit diverse data center liquid‑cooling loops, while also supporting multi‑vendor solutions.
• Advanced Liquid Cooling Solutions: Targeting 4 kW class chip thermal capability, the portfolio includes high‑efficiency cold plates, AALC, in‑row CDUs, and liquid‑cooling management. It balances reliability, serviceability, and scalability to deliver efficient, sustainable cooling for AI/HPC workloads.

"AI is rapidly entering an era of higher power and larger package footprints. Meeting fast‑evolving compute‑density demands requires out‑of‑the‑box thinking," said William Lin, President and CEO at Wiwynn. "Our double‑wide rack breaks traditional limits, delivering rack‑level optimization across compute and signal integrity while uniting HVDC power and liquid‑cooling technologies to build the efficient, scalable, and sustainable infrastructure needed for next‑generation AI. We look forward to partnering with OCP ecosystem partners to bring these designs into practical deployments.

Visit Wiwynn @OCP 2025 (Booth B13, San Jose Convention Center ) , join our engineering workshop sessions and download our latest whitepapers to explore the latest innovations shaping the future of AI infrastructure and data center technologies.

About Wiwynn

Wiwynn is an innovative cloud IT infrastructure provider of high‑quality computing and storage products, plus rack solutions for leading data centers. We are committed to the vision of "unleash the power of digitalization; ignite the innovation of sustainability." The company aggressively invests in next‑generation technologies to provide the best TCO, workload, and energy‑optimized IT solutions from cloud to edge.

For more information, please visit Wiwynn website, Facebook, and Linkedin.

View original content to download multimedia:https://www.prnewswire.com/news-releases/wiwynn-debuts-double-wide-rack-architecture-for-nextgeneration-ai-at-ocp-global-summit-2025-302581337.html

SOURCE Wiwynn