Frequency-guided inter-layer KV sharing with logit-aware head routing nearly matches full-cache long-context accuracy at about 3.9× lower peak KV memory.
Rest-kv: Robust kv cache eviction with layer-wise output reconstruction and spatial-temporal smoothing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
Frequency-guided inter-layer KV sharing with logit-aware head routing nearly matches full-cache long-context accuracy at about 3.9× lower peak KV memory.