Story
arxiv_cs_cl ยท Nov 19, 2026 ยท paper
Source brief
RoCoKV: Accelerating LLM Inference Serving through Uncertainty and Redundancy Aware KV Cache Compression
arxiv.orgNov 19, 2026
original source linked
In brief
KV cache compression is critical for large reasoning models, where most of the cost comes from long generated reasoning traces rather than the input prompt. These traces often contain redundant and low-utility tokens...
Feed lens
eval