GRIK: Grouped Relevance-Integrated Key Pruning for Grouped-Query Attention LLMs

The key–value (KV) cache is a major memory bottleneck in long-context inference, and existing K-channel pruning does not shrink it under grouped-query attention (GQA): in the evaluated implementations, ThinK materializes K and V per query head ($3.20\times$ total KV) and SparK reconstructs a full-width cache ($1.00\times$). We identify two structural conditions, a mask shared across the query heads of each KV group and across all cached tokens, under which channel pruning yields a dense shared-key cache whose width equals the retained channel count. We introduce GRIK, a training- and calibration-free method that satisfies both conditions by construction and derives a prompt-adaptive mask per KV head from output-projection influence, key-projection norms, and attention energy. At 40% K-channel pruning, GRIK stores K at $0.60\times$ and total K+V at $0.80\times$ the bf16 baseline. Without token eviction, its LongBench average is within $0.23$ points of Full KV on three GQA backbones; with H2O eviction it is the best non-Full-KV method in 19 of 24 (model, budget, ratio) cells, and at approximately matched total-KV memory it improves over H2O alone by $1.55$–$1.62$ points. The reduction composes with other axes: adding GRIK to SnapKV, FP8, or int4 KV changes LongBench by at most $0.21$ points while cutting total KV to as low as $0.20\times$. On RULER, its eight exact-retrieval tasks average at least $99.0\%$ through 32K, although the 13-task average trails Full KV by $6.90$–$8.59$ points. In a fixed-memory H100 serving test at 50% pruning, the smaller cache admits $1.33\times$ more concurrent sequences and raises aggregate request throughput by $1.10\times$, with per-user decode latency $1.35\times$ that of the baseline at the higher concurrency. Code and configurations are available at https://anonymous.4open.science/r/GRIK/.