
OpenAI and Broadcom Unveil "Jalapeño," a Custom LLM Inference Chip to Reduce Reliance on Nvidia
OpenAI and Broadcom unveiled Jalapeño, OpenAI's first custom AI inference chip, developed in just nine months with the help of OpenAI's own models. The ASIC is designed to cut inference costs by roughly 50% and will be deployed at gigawatt-scale data centers by end of 2026.
3 months ago























