< Back to all clusters
[TECHNOLOGY] · United States · 69 sources

started · updated

OpenAI launches Jalapeño AI inference chip with Broadcom

OpenAI announced Jalapeño, its first custom‑designed AI inference processor, developed in partnership with Broadcom and system integrator Celestica. The chip is built from scratch for large‑language‑model (LLM) inference – the stage where models like ChatGPT generate responses – and was taken from initial design to tape‑out in nine months, a record speed for high‑performance ASICs. Early lab tests indicate substantially higher performance‑per‑watt than existing state‑of‑the‑art solutions, with engineering samples already running workloads such as GPT‑5.3‑Codex‑Spark.

OpenAI President Greg Brockman said, “Jalapeño is part of our long‑term full‑stack infrastructure strategy to make compute more abundant, resulting in AI that is faster, more reliable, more affordable for people and businesses.” The chip will be deployed in data‑center racks starting at the end of 2026, initially in Microsoft‑operated facilities, and forms the first step of a multi‑generation compute platform intended to reduce OpenAI’s reliance on external GPU suppliers such as Nvidia. Broadcom CEO Hock Tan highlighted the partnership as a “fundamental commitment to scaling the physical infrastructure required for the next decade of AI.”

Sources

3 months ago
- Cyprus Shipping News [cyprusshippingnews.com]
3 months ago
3 months ago
3 months ago
3 months ago