OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boss, Mark, Voleti, Vikram, Donné, Simon, Vainer, Shimon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!