/Technology
OpenAI unveils its first custom chip, built by Broadcom
OpenAI announced the Jalapeño chip, a purpose‑built inference processor that promises higher performance‑per‑watt than existing GPUs.
OpenAI announced the Jalapeño chip, a purpose‑built inference processor that promises higher performance‑per‑watt than existing GPUs.
OpenAI and Broadcom announced a custom AI chip that could cut inference costs by about 50%, boosting the speed of large language models.
OpenAI and Broadcom launch Jalapeño, a custom AI inference chip designed to accelerate large language model workloads with higher performance per watt.