kapynInfrastructure

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

OpenAI's Jalapeño chip delivers record inference speed and efficiency. Tested on Semianalysis's InferenceX benchmark, it yields more tokens per user and higher throughput per kilowatt than current state-of-the-art. The custom silicon targets fast, scalable AI inference for production workloads.

TechCrunch AI·Aug 25, 2026

Opening Kapyn…