Our Creators are driving towards one goal – dropping the hardware costs required to train large AI models by >1000x – but as AI hardware and techniques advance rapidly, our baseline metrics and the computational cost of MLPerf benchmark workloads shift, requiring a constant recalibration of our targets. Now, we're looking for a team who can help track these moving targets and publish their findings to the research community. Through this work, we'll create an accurate (and open) source of ground truth for programme targets, and ensure the ambitious technologies developed by our Creators are measured against the most up-to-date advances in the field.
