AnchorKV compresses the KV cache 20x with near-lossless accuracy by representing each token as an anchor projection plus selectively allocated quantized residuals, beating eviction baselines at matched byte budgets on three model scales.
Bashatah and Aurang Zaib , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AnchorKV: Anchor-Residual KV Cache Compression
AnchorKV compresses the KV cache 20x with near-lossless accuracy by representing each token as an anchor projection plus selectively allocated quantized residuals, beating eviction baselines at matched byte budgets on three model scales.