Remix.run Logo
High-Fidelity KV Cache Summarization Using Entropy and Low-Rank Reconstruction(jchandra.com)
14 points by jchandra 2 days ago | 1 comments
vivahir215 2 days ago | parent [-]

Interesting Approach. Curious about the latency tradeoff: OLS + SVD are much heavier than Top-K.Have you benchmarked end-to-end inference latency?