OpenAI unveils Jalapeño, its first custom AI processor for inference
TL;DR
OpenAI, with Broadcom, unveils Jalapeño, its first AI inference ASIC for servers—designed to power current and future models with better performance per watt and less reliance on Nvidia GPUs, and dubbed the first step in a multi-generation compute platform set for deployment by the end of 2026.
- OpenAI reveals its first AI processor: Jalapeño The Verge
- OpenAI and Broadcom unveil LLM-optimized inference chip OpenAI
- OpenAI unveils first chip as part of Broadcom deal in effort to 'build the full stack' CNBC
- OpenAI just announced its first custom chip to help ChatGPT run better CNN
- OpenAI and Broadcom announce first custom AI chip, in strike at Nvidia Yahoo Finance
Want the full story? Read the original reporting
Read on The Verge