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.
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.
<iframe src="https://statesidedaily.com/embed/cluster/d3f13f7d8b80e440680fce8a9cb8fc2a6ca8257c" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show"></iframe>
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.
