StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
This addresses efficiency issues in long-context inference for AI practitioners, representing an incremental improvement over existing compression methods.
The paper tackles the memory and bandwidth bottlenecks in large language models with long contexts by proposing StructKV, a KV cache compression framework that preserves global structural information, achieving effective preservation of long-range dependencies and retrieval robustness on benchmarks.
As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context inference. Existing compression approaches typically prioritize tokens based on local saliency metrics to decouple prefill computation from decoding memory. However, these methods often rely on local saliency snapshots at a specific layer, thereby systematically discarding tokens that act as global information hubs across the network depth but appear temporarily dormant at the specific layer selected for pruning. To address this limitation, we propose StructKV, a structure-aware KV cache compression framework that introduces three core innovations: First, Global In-Degree Centrality aggregates attention patterns across the network depth to identify global information hubs. Second, Dynamic Pivot Detection utilizes information-theoretic metrics to adaptively locate the optimal layer for compression. Finally, Structural Propagation and Decoupling separates the computational budget from the memory storage budget. Experimental results on the LongBench and RULER benchmarks demonstrate that StructKV effectively preserves long-range dependencies and retrieval robustness.