KVpop -- Key-Value Cache Compression with Predictive Online Pruning

Researchers introduced KVpop, a method that compresses key-value caches in autoregressive decoding by learning a fixed-budget eviction policy through direct supervision.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.