TechFlow news, June 30, according to The Information, a source revealed that earlier this month, OpenAI engineers told some colleagues that leveraging several newly developed optimization technologies, they found a solution that could reduce model inference costs by more than half. After engineers applied this new technology to scenarios where visitors without free or paid accounts use ChatGPT, they at one point reduced the required number of NVIDIA graphics processing units (GPUs) to only a few hundred.
Add to Favorites
Share to Social Media
