04:00
2026-07-21
machinebrief.com
artificial-intelligence
C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
Researchers propose C$^2$KV, a unified framework for non-prefix KV cache reuse that jointly optimizes KV extraction and inference-time concatenation, achieving up to 17× inference speedup under long c…