OpenAI has unveiled Jalapeño, its first custom AI chip, developed in partnership with Broadcom to reduce its reliance on Nvidia GPUs for inference workloads. The chip is designed specifically for OpenAI’s inference systems and is reported to deliver better performance-per-watt than existing alternatives. OpenAI said the chip is an early step in a broader strategy to optimize its computing infrastructure across the full technology stack, from chip design to deployment.
