QCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query Processing
QCATS slices transformer FFNs using query predicates, cutting in-database inference latency up to 4.42x.
1 stories, newest first · one card per story
QCATS slices transformer FFNs using query predicates, cutting in-database inference latency up to 4.42x.
Today 721 readers · 854 views · 278 reads · all time 187K views