Q.ANT, a developer of photonic processing for AI, has launched a dedicated production line for thin-film lithium niobate (TFLN)-based photonic chips at the Institute of Microelectronics Stuttgart (IMS CHIPS). The integration of Q.ANT’s photonic chip technology and the upcycling of the existing CMOS production facility at IMS CHIPS creates a blueprint for cost-effectively modernizing chip production worldwide, the partners said. The line is expected to accelerate the production of energy-efficient, high-performance processors for AI applications by delivering faster, more energy-efficient processors to meet the growing computational demands of AI and high-performance computing (HPC). Q.ANT has invested €14 million ($14.7 million) in machinery and equipment to complement the new line for photonic chips. (From left): Q.ANT CEO Michael Förtsch; minister of economic cffairs of the state of Baden-Württemberg, Nicole Hoffmeister-Kraut; and director and CEO of IMS CHIPS Jens Anders. The trio present an enlarged, symbolic photonic wafer based on thin-film lithium niobate to enable faster, more energy-efficient AI and high performance computing applications. Courtesy of Q.ANT. “With this pilot line, we are accelerating time to market and laying the foundation for photonic processors to become standard coprocessors in high-performance computing,” said Michael Förtsch, CEO of Q.ANT. “By 2030, we aim to make our photonic processors a scalable, energy-efficient cornerstone of AI infrastructure.” Capable of producing up to 1000 wafers per year, the pilot line is specifically designed for production using TFLN, which enables ultra-fast optical signal manipulation at several GHz without the need for heat to modulate the light on the photonic circuit. The line’s establishment enables Q.ANT to refine its chip architecture to meet evolving market requirements. It also serves as the R&D basis for Q.ANT's photonic native processing units and native processing server (NPS) solutions designed to power high-performance computing data centers. According to Q.ANT, its NPS solutions aim to accelerate key workloads, include AI model training and inference; scientific and engineering simulations; real-time processing of complex mathematical equations; and high-density tensor operations for machine learning. According to the partners, the manufacturing method could enable countries to attain greater semiconductor manufacturing resilience, reduce dependency on global supply chains, and accelerate the development of critical technologies that drive innovation across data centers, research institutions, and advanced industries. The development stems from an agreement between Q.ANT and IMS CHIPS signed in 2023. "By partnering with Q.ANT, we are leveraging our semiconductor manufacturing expertise to accelerate the industrialization of photonic processors and establish a scalable model for energy-efficient computing — a crucial step for the future of AI,” said Jens Anders, director and CEO of IMS Chips. Q.ANT is a 2018 spinout from TRUMPF R&D. The company has earned support from TRUMPF since its establishment, including an eight-figure investment in 2021, as well as numerous partnerships and consortia.