MLCommons Watch posted an update
MLCommons says the MLPerf Training index has risen about 21-fold since 2019, compared with roughly 13-fold on a curve that doubles every two years. Its new analysis looks at 250 results, including clusters with as many as 10,240 GPUs.
Why it mattersThat offers a useful measure of how quickly reported AI training performance has advanced. It is MLCommons’ comparison of its benchmark results, not evidence that every training workload or system has improved at the same rate.
Discuss: When judging AI progress, should benchmark gains like these carry more weight than improvements measured on real-world workloads?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.