Inline Hardware KV-Cache Compression for Long-Context Transformer Inference: An Architectural Case for a Memory-Path Compression Engine

Jakubův, Jan, Chvalovský, Karel, Goertzel, Zarathustra et al.

2023 · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 77,005 citations

As a present to Mizar on its 50th anniversary, we develop an AI/TP system that automatically proves about 60% of the Mizar theorems in the hammer setting. We also automatically prove 75% of the Mizar theorems when the automated provers are helped by using only the premises used in the human-written Mizar proofs. We describe the methods and large-scale experiments leading to these results. This includes in particular the E and Vampire provers, their ENIGMA and Deepire learning modifications, a number of learning-based premise selection methods, and the incremental loop that interleaves growing…

Read the paper →

Explore this paper's citation graph on Constellation.