OpenAI Jalapeño芯片基准测试显示推理性能大幅领先
原标题：OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show
AI 摘要
OpenAI在Hot Chips会议上公布了其定制推理芯片Jalapeño的详细信息和首批基准测试结果。在Semianalysis的InferenceX基准测试中，Jalapeño在每用户token数和每千瓦吞吐量上均优于当前最先进的Nvidia Blackwell系统。该芯片由OpenAI与博通合作开发，旨在减少推理过程中的预填充和通信延迟，计划于2026年底小规模部署，2027年更大规模推出。
正文节选
At the Hot Chips conference on Tuesday, OpenAI shared a more detailed look at Jalapeño, including the first batch of benchmark results for the new system. Tested on Semianalysis’s InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the-art inference processors. “The bottom line is that the results show a very, very significant performance advance over state of the art,” said Richard Ho, OpenAI’s head of hardwa