OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show

Tested on SemiAnalysis’ InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the art.

延伸阅读

1. Anthropic无法可靠控制AI智能体，切断内部评估的实时互联网访问
2. Prime Agent 用 Rust 重写：2000 个 AI 智能体协作完成自我重写
3. 乌克兰无人机袭击俄罗斯AI数据中心，Yandex超级计算机受损