AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
ParoQuant: Pairwise Rotation Quantization
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
-
AXELRAM: Quantize Once, Never Dequantize
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.