KV cache compression on 5 sequences Seq 2 hard
0.143KL DivergenceKVSCULPT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| KVSCULPTCompression ratio (r)=0.3, Retain zone (m)=256, Optimization method=L-BFGS, Synthetic future queries=128, V solver=ridge regression2026.03 | 0.143 | 1.8 | |
| Select+FitCompression ratio (r)=0.3, Retain zone (m)=256, V solver=ridge regression2026.03 | 0.261 | — |