OpenAI and Broadcom Unveil Jalapeño, a Custom LLM Inference Chip

OpenAI and Broadcom have introduced Jalapeño, a custom AI chip engineered specifically for large language model inference. The companies say the silicon is optimized to improve performance, efficiency, and scalability across modern AI systems.

The move signals OpenAI's deepening push into custom hardware, reducing reliance on general-purpose accelerators as inference demand surges. By tailoring chip design to the realities of LLM workloads, the partnership aims to drive down the cost and energy footprint of running AI at scale.