26.06.2024 13:09 Uhr, Quelle: Toms Hardware

AI researchers found a way to run LLMs at a lightbulb-esque 13 watts with no loss in performance

Elimination of matrix multiplication from LLM processing can massively increase performance-per-watt with the correct optimizations, researchers from UC Santa Cruz demonstrate. It remains to be seen how applicable this approach is for AI in general.

Weiterlesen bei Toms Hardware