Existing procedures seek configurations that minimize expected runtime.

ASPEN also achieves high resource utilization and memory reuse by letting each resource asynchronously traverse depthwise in the DNN graph to its full computing potential.

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length.

Work completed at the University of Washington. Work completed at Microsoft Research.

In this paper, we make progress towards addressing these issues. We introduce Greedy Rejection Coding (GRC), which generalises the rejection based-algorithm of Harsha et al.

As a result, it tractably draws samples even when the matrices forming the Khatri-Rao product have tens of millions of rows each.