VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch

Wed, 09 Sep 2026 00:00:00 +0900

Paper

VestigeKV: The Degenerate RoPE Branch Carries Its Own Cache Eviction Signal

TL;DR

In NoPE-MLA models (Kimi Linear 48B), reading only 11% of each row — the 64-dim decoupled branch that training has repurposed as a salience channel, a “vestige” of RoPE — yields a query-independent importance signal and achieves 8–32× (up to 128× with the retrieval tier) KV cache compression while maintaining retrieval performance. It is a pure cache policy that never touches weights, kernels, or compute (source: Abstract).

2609.03949v1 on Jaehun's Blog

VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch

VestigeKV: The Degenerate RoPE Branch Carries Its Own Cache Eviction Signal

TL;DR