Better scheduling and resource-sharing for inferencing workloads using multiple models, not a training breakthrough ...
Scheduler squeezes more work from fewer H20 accelerators Alibaba Cloud boffins have emerged from their smoke filled labs ...
Alibaba Group has launched a computing pooling system, Aegaeon, which reportedly reduces the use of Nvidia GPUs in its AI ...
This innovation was tested in Alibaba Cloud's model marketplace for over three months, according to a research paper ...
The new Aegaeon system can serve dozens of large language models using a fraction of the GPUs previously required, potentially reshaping AI workloads.
Alibaba Cloud has beta-deployed the solution in its model marketplace, where it is serving tens of models. The company claims ...
Tom's Hardware on MSN
Alibaba Cloud says it cut Nvidia AI GPU use by 82% with new pooling system— up to 9x increase in output lets 213 GPUs perform like 1,192
Alibaba Cloud claims its new Aegaeon pooling system reduced the number of Nvidia GPUs required to serve large language models ...
Investing.com -- Alibaba Cloud has published a paper detailing its Aegaeon GPU resource optimization solution for large language model (LLM) concurrent inferencing, the company announced Monday. The ...
China is both communist and working passably well, something he and the United States generally are being forced reluctantly ...
Stocktwits on MSN
NVDA Stock Rises Premarket: First US-Made Blackwell Chip Revealed, While Alibaba’s New Tech Cuts Nvidia GPU Usage By 82%
Nvidia Corp. (NVDA) stock rose moderately in Monday’s early premarket session as traders digested mixed catalysts concerning ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback