TreeKV uses a cyclic pair-wise eviction tree with averaged attention scores to compress LLM KV caches, reporting SOTA perplexity on PG19/OpenWebText2 and best LongBench averages.
Scissorhands: Ex- ploiting the persistence of importance hypothesis for llm kv cache compression at test time
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TreeKV: Smooth Key-Value Cache Compression with Tree Structures
TreeKV uses a cyclic pair-wise eviction tree with averaged attention scores to compress LLM KV caches, reporting SOTA perplexity on PG19/OpenWebText2 and best LongBench averages.