ReSA keeps sparse decoding accurate by refreshing the KV cache with dense attention every f tokens, achieving near-lossless quality with a large speedup.
Flash-Decoding for long-context inference.https://crfm.stanford.edu/2023/10/12/flashdecoding.html, 2023
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Rectified Sparse Attention
ReSA keeps sparse decoding accurate by refreshing the KV cache with dense attention every f tokens, achieving near-lossless quality with a large speedup.