SlimKV (EMNLP 2026 Oral): joint token-feature KV compression with reconstruction-free decoding. r2/r4/r8 = 2×/4×/8× feature compression.
-
SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention
Paper • 2610.02953 • Published -
Zihant0513/SlimKV-Llama3.1-8B-r2
Text Generation • 9B • Updated • 412 -
Zihant0513/SlimKV-Llama3.1-8B-r4
Text Generation • 9B • Updated • 470 -
Zihant0513/SlimKV-Llama3.1-8B-r8
Text Generation • 9B • Updated • 481