OpenAI announces Jalapeño custom inference chip built with Broadcom to reduce Nvidia dependency

According to TechCrunch, OpenAI announced Jalapeño, a custom inference chip developed with Broadcom, to reduce reliance on Nvidia's market dominance. The move joins Google, Apple, and SpaceX in building proprietary silicon to achieve single-supplier risk mitigation and hardware tuned to specific performance needs. TechCrunch noted the strategy aims for performance gains similar to those Apple achieved when transitioning from Intel.