OpenAI is planning to launch its first in-house AI chip next year. This strategic move aims to reduce the company’s dependence on Nvidia, the current dominant supplier of AI chips.
OpenAI’s Proprietary Chip
According to a recent Reuters report, OpenAI will finalize the design of its custom chip in the coming months. Fabrication will occur at Taiwan Semiconductor Manufacturing Co. (TSMC), utilizing their advanced 3-nanometer technology. This cutting-edge chip will feature “high-bandwidth memory” and “extensive networking capabilities,” optimizing performance for demanding AI workloads.
Initially, OpenAI plans to deploy its custom chip on a limited scale, primarily for running AI models within its infrastructure. However, this marks the beginning of a long-term strategy to develop a series of increasingly sophisticated in-house AI chips.
This move comes amidst a growing trend among tech giants to develop their own AI hardware. Companies like Google and Meta have invested heavily in custom chip development to gain greater control over their AI infrastructure and reduce reliance on external suppliers.
OpenAI’s chip design team, led by former Google TPU engineer Richard Ho, has expanded to address the growing competition in the AI hardware market. This aims to gain a competitive edge, improve efficiency, and reduce reliance on external suppliers by developing AI chips.
Started his freelancing adventure in 2018 and began doing freelance Audio Engineering work and then started freelance writing a few years later.
Currently he writes for Gadget Pilipinas and Grit.PH.
He is also a musician, foody, gamer, and PC enthusiast.
