Jalapeño’s first results show industry-leading speed and efficiency in AI inference
中文摘要
OpenAI推出了定制推理芯片Jalapeño，旨在显著提升AI推理的速度、能效与吞吐量，并降低延迟。
English Summary
OpenAI's custom Jalapeño chip delivers industry-leading speed, power efficiency, higher throughput, and lower latency for AI inference.
原文节选
Jalapeño is a custom inference chip from OpenAI that delivers faster, more power-efficient AI inference, with higher throughput and lower latency for modern models.