High-Fidelity KV Cache Summarization Using Entropy and Low-Rank Reconstruction

3 comments

• $vivahir215 8 hours ago

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

  [-]
  • $jchandra 8 hours ago

    [dead]

• $jchandra 8 hours ago

  [dead]