OpenAI and Broadcom Unveil 'Jalapeño' AI Accelerator for LLM Inference
On June 24, OpenAI and Broadcom introduced the Jalapeño AI accelerator, a custom chip designed to enhance large language model (LLM) inference. The processor aims to deliver better performance-per-watt than current alternatives and marks OpenAI's shift toward full-stack integration of hardware and product development.
Tickers: $AVGO