most citedKV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2024★ 1 cited

KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head

Isaac Rehg

Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently…