OpenAI Jalapeño chip delivered 1.5 to 1.9 times more AI work per watt at peak throughput and 1.7 to 3.6 times lower end-to-end latency than the comparison systems. For highly interactive workloads, it delivered 2.1 to 4.1 times higher performance. In June, OpenAI unveiled the chip program in partnership with Broadcom, built from a blank ...

Read more

---

Link :
https://www.nextbigfuture.com/2026/08/openai-jalapeno-inference-chip-just-announced-at-hot-chips.html