LFPS predicts which KV cache positions a decoder will attend to by reusing historical vertical and slash patterns plus local expansion, then runs exact Top-k only on the predicted candidate set.
Loki then and now: the trickster against civilization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learn from the Past: Fast Sparse Indexing for Large Language Model Decoding
LFPS predicts which KV cache positions a decoder will attend to by reusing historical vertical and slash patterns plus local expansion, then runs exact Top-k only on the predicted candidate set.