KV cache compression on 5 sequences Mean
0.0575KL 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 | 0.0575 | 4.1 | |
| Select+FitCompression ratio (r)=0.3, Retain zone (m)=256, V solver=ridge regression2026.03 | 0.233 | — |