AI RESEARCH
IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression
arXiv CS.LG
•
ArXi:2603.28430v1 Announce Type: new Orthogonal feature decorrelation is effective for low-bit online vector quantization, but dense random orthogonal transforms incur prohibitive $O(d^2)$ storage and compute. RotorQuant reduces this cost with blockwise $3$D Clifford rotors, yet the resulting $3$D partition is poorly aligned with modern hardware and offers limited local mixing. We propose \textbf{IsoQuant}, a blockwise rotation framework based on quaternion algebra and the isoclinic decomposition of $SO(4.