List your company

KV Cache Quantization on LLaMA-7B

0.01Delta Perplexity (ΔPPL)KVQuant-4b-1%
0.0090.00950.010.0105Mar 29, 2026

Evaluation results

MethodLinks
KVQuant-4b-1%Total bits=4.32, Calibration=Yes2026.030.01