Amid us export curbs, this innovation enhances ai efficiency and scalability for cloud providers. Alibaba introduces aegaeon, a computing pooling system reducing nvidia gpu reliance by 82%. Alibaba group holding has introduced a computing pooling solution that it said led to an 82 per cent cut in the number of nvidia graphics processing units (gpus) needed to serve its artificial.
Laila Gomez - Age, Height, Net Worth, Boyfriend, Bio, Wiki, Facts
According to a report from south china morning post, aegaeon allows a single gpu to serve multiple ai models at once, drastically reducing the total hardware needed
In testing, the system cut the number of nvidia h20 gpus required to serve dozens of models — some with up to 72 billion parameters — from 1,192 to just 213.
