OFC 2025 MARVELL DEMOS SIPHO LIGHT ENGINE FOR AI NETWORKS

Low-loss liquid-cooled power supply 2025 model

Low-loss liquid-cooled power supply 2025 model

Key features of the showcase include complete power solutions for both 800 VDC and ±400 VDC power architectures, the newly-launched liquid-to-liquid (L2L) CDU with 2,000kW of cooling capacity for new AI data centers, the new 300kW liquid-to-air (L2A) CDU for. , October 6th, 2025 — Delta, a global leader in power management and smart green solutions, will present its next-generation of highly integrated high-voltage DC power distribution, advanced precision cooling, and networking solutions for AI data centers at the OCP Global Summit. The iHP20S Liquid Cooled precision AC-DC configurable power supply is 100% digitally controlled in a 757. 8 mm package and provides eight individual slots that accept intelligent DC-DC converter modules. Its cooling is handled by the PC's custom liquid cooling setup, which means that. The PSU channels coolant through heatsinks that come into contact with the hottest components, such as switching MOSFETs, Schottky diodes, APFC, IGBTs, and more.

Read More
Ofc optical cable

Ofc optical cable

Modern fiber-optic communication systems generally include optical transmitters that convert electrical signals into optical signals, to carry the signal, optical amplifiers, and optical receivers to convert the signal back into an electrical signal.

Read More
Which AI server QSFP provider is the best

Which AI server QSFP provider is the best

Based on our deployment experience, OSFP is the clear winner for: AI/ML Clusters: GPU interconnects running at full load generate immense heat. Next-Gen Cloud Core: For 800G backbones where backward compatibility is less important than raw performance. Beyond providing the physical hardware, customers have come to expect AI server Original Equipment Manufacturers (OEMs) to offer cooling technology, infrastructure management software, and professional services. In the rapidly evolving landscape of high-performance computing and AI infrastructure, NVIDIA optical transceivers have emerged as critical components for enabling next-generation 800G network deployments. This guide explores key technical features for GPU clusters, examines spine-leaf architectures for distributed AI applications, and evaluates whether QSFP-DD or OSFP is better suited for future AI data centers. However, with multiple form factors—QSFP-DD, QSFP112, and OSFP—each tailored to specific deployment and upgrade needs, choosing the right 400G NIC is no simple task.

Read More
AI intelligence benefits optical modules

AI intelligence benefits optical modules

Optical modules convert electrical signals into light to move data quickly and reliably in AI systems, enabling fast and smooth data processing. The integration of artificial intelligence (AI) in optical technologies is reshaping multiple sectors. As AI models grow in size and complexity, they demand unprecedented levels of computing power, which in turn requires massive amounts of data to be moved quickly and.

Read More
Maximum power consumption of AI server

Maximum power consumption of AI server

AI servers consume significantly more power than traditional IT equipment, primarily due to the use of GPUs and high-performance accelerators. Typical ranges include: • Traditional servers: 300–800 W per server • GPU servers: 2–10 kW per server • AI racks: 20–100+ kW per rackWhere traditional server racks once operated at around 5–10 kW, modern AI environments are pushing far beyond that, often reaching 30 kW, 60 kW or even over 100 kW per rack. According to RAND Corporation research, AI data centers could require 68 gigawatts of power capacity globally by 2027, close to California's entire power grid. Today, a single NVIDIA GB200 NVL72 AI rack draws 132 kW — more than 16 times as much. It's a fundamental rewrite of how data centers provision, generate, store, and back up power. The IEA's latest report, Key Questions on Energy and AI (April 2026), puts the updated trajectory plainly: consumption will roughly double and reach almost 500 TWh in.

Read More

Get In Touch

Connect With Us

📱

Poland (Sales & Engineering HQ)

+48 22 538 72 19

📍

Headquarters & Manufacturing

ul. Postępu 14, 02-676 Warszawa, Poland