this post was submitted on 09 Jan 2024
7 points (100.0% liked)

Technology@stad

63 readers
16 users here now

Technology News and Opinion

founded 1 year ago
7
Frontier trained a ChatGPT-sized large language model with only 3,000 of its 37,888 Radeon GPUs (www.tomshardware.com)
submitted 9 months ago by vidarh@lemmy.stad.social to c/tech@lemmy.stad.social
0 comments fedilink hide all child comments
 

The world's fastest supercomputer blasts through one trillion parameter model with only 8 percent of its MI250X GPUs

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here