arXiv cs.LG
· Papers
How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit
arXiv:2607.11942v1 Announce Type: new Abstract: KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the economic case for a compressed KV cache is reuse: compress a document once, answer many future questions against it. In th