Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation
This work rethink KV cache eviction through the lens of local information geometry, modeling the attention process as a nonlinear Gaussian communication channel, and derives the Jacobian Information Capacity, a novel objective that explicitly captures query relevance, softmax sensitivity, and structural diversity.
Jia-Ming Yang, Chenwei Tang, Liang-Li Zhen et al.
· 0 citations