A team of researchers developed “parallel optical matrix-matrix multiplication” (POMMM), which could revolutionize tensor processing by enabling a single light source to perform multiple operations ...

Up until late 2024, no one has been able to massively increase the amount of compute dedicated to a single model beyond the OpenAI GPT 4 model level. This information is from semianalysis and EIA.

Google’s in-house Tensor chips have steadily improved over the years to become a reliable daily driver with solid battery efficiency. Still, performance has often been a sticking point. While previous ...