Tensordyne says logarithmic computing could reduce AI inference costs and power demands, offering an alternative to conventional chip designs.

D-Matrix says its chips can run inference workloads 10 times faster and using five times less energy than a standalone graphics processing unit from Nvidia. Like Cerebras, D-Matrix is trying to prove ...

The Marshall Project is a journalism outlet, not an advocacy organization. We don’t approach any issue with an outcome in mind. Our reporters examine all sides of an issue and follow the facts where ...