Source item
Open original source ↗OpenAI says that it is preparing to operate Jalapeño at scale and validating performance across more models, with initial deployments expected before year end.
$AVGO $NVDA $AMD
Quoted context
These are the quoted author’s words.
OpenAI says that its new Jalapeño chip delivered 1.5X to 1.9X higher tokens per watt at peak throughput and 1.7X to 3.6X lower latency versus Nvidia’s $NVDA GB200 and GB300 on GPT‑OSS 120B, DeepSeek R1, and Kimi K2.5 1T models. $AVGO $AMD
Beth_Kindig ↗