OpenAI Cuts Inference Costs by Over 50%, GPU Usage Drops to Hundreds from Tens of Thousands

According to sources cited by media outlets, OpenAI achieved a major technical breakthrough earlier this month, cutting inference costs by more than 50% and dramatically reducing GPU requirements. Internal engineers presented the breakthrough, revealing that the new optimization approach reduced GPU usage to just hundreds of units when handling ChatGPT visitor requests, compared to tens of thousands of high-end chips previously required.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments