OpenAI reveals first custom AI chip 'Jalapeño,' accelerating move away from Nvidia
Translated from Korean, summarized and contextualized by DistantNews.
At a glance
- OpenAI has unveiled its first custom AI chip, codenamed 'Jalapeño,' developed with Broadcom.
- The chip is designed for inference tasks and aims to reduce reliance on Nvidia.
- OpenAI plans to deploy these chips in its data centers by the end of the year.
OpenAI, the creator of ChatGPT, has officially revealed its first in-house developed AI chip, codenamed 'Jalapeño.' The chip was co-developed with Broadcom and is specifically designed for artificial intelligence inference tasks.
This move signifies OpenAI's accelerating efforts to develop and implement its own AI hardware, joining the ranks of tech giants like Google, Amazon, Microsoft, and Meta. The development is seen as a strategic step to decrease dependence on Nvidia, the current dominant supplier of AI chips.
OpenAI and Broadcom announced their intention to deploy the 'Jalapeño' chips in actual data centers starting from the end of this year. This initiative underscores the growing trend of major AI developers investing in custom silicon to optimize performance and manage costs.
The development of custom AI chips allows companies to tailor hardware specifically to their unique needs, potentially leading to greater efficiency and innovation in AI model deployment and operation.
Originally published by Chosun Ilbo in Korean. Translated, summarized, and contextualized by our editorial team with added local perspective. Read our editorial standards.