Jalapeño’s first results show industry-leading speed and efficiency in AI inference
OpenAI reported first benchmark results for its custom Jalapeño inference chip, claiming higher throughput, lower latency, and better power efficiency.
Excerpt
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.
Read at source: https://openai.com/index/jalapeno-first-results