OCTOPUS compresses KV caches via octahedral parametrization of rotated triplets and squared-error-optimized Lloyd-Max quantization, matching or exceeding prior rotation codecs with growing gains at low bit widths.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
OSCAR achieves near-BF16 accuracy for 2-bit KV cache quantization by using offline spectral covariance-aware rotations aligned with attention, plus a custom deployable INT2 kernel compatible with paged serving.
citing papers explorer
-
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
OCTOPUS compresses KV caches via octahedral parametrization of rotated triplets and squared-error-optimized Lloyd-Max quantization, matching or exceeding prior rotation codecs with growing gains at low bit widths.
-
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
OSCAR achieves near-BF16 accuracy for 2-bit KV cache quantization by using offline spectral covariance-aware rotations aligned with attention, plus a custom deployable INT2 kernel compatible with paged serving.