FibQuant is a universal fixed-rate vector quantizer for KV-cache compression that uses a radial-angular codebook matched to the spherical-Beta source after Haar rotation and strictly outperforms scalar quantization at matched rates.
The total cost isO(L+N/L), minimized atL= √ Nwith total workΘ( √ N)perk-block
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
FibQuant is a universal fixed-rate vector quantizer for KV-cache compression that uses a radial-angular codebook matched to the spherical-Beta source after Haar rotation and strictly outperforms scalar quantization at matched rates.