Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approaches predominantly rely on query-key attention scores to rank and evict cached tokens, assuming that attention intensity correlates with semantic importance. However, this heuristic overlooks the contribution of value vectors, which directly influence the attention output. In this paper, we propose CurDKV, a novel, value-centric KV compression method that selects keys and values based on leverage scores computed from CUR matrix decomposition. Our approach approximates the dominant subspace of the attention output $softmax(QK^T)V$, ensuring that the retained tokens best preserve the model's predictive behavior. Theoretically, we show that attention score approximation does not guarantee output preservation, and demonstrate that CUR-based selection minimizes end-to-end attention reconstruction loss. Empirically, CurDKV achieves up to 9.6% higher accuracy than state-of-the-art methods like SnapKV and ChunkKV under aggressive compression budgets on LLaMA and Mistral, while maintaining compatibility with FlashAttention and Grouped Query Attention. In addition to improved accuracy, CurDKV reduces generation latency by up to 40% at high compression, offering a practical speed-accuracy tradeoff.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Information Compression and Performance Evaluation of Tic-Tac-Toe's Evaluation Function Using Singular Value Decomposition
We approximated the evaluation function for the game Tic-Tac-Toe by singular value decomposition (SVD) and investigated the effect of approximation accuracy on winning rate. We first prepared the perfect evaluation funct…
Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing
Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression,…
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitate LLM compression methods for practical deployment. Singular Value Decomposition (SVD) offers a promising so…
Language ModelingLanguage ModellingLarge Language ModelModel CompressionActivation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment. We present a novel low-rank compression …
Model CompressionSVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
Despite significant advancements, the practical deployment of Large Language Models (LLMs) is often hampered by their immense sizes, highlighting the need for effective compression techniques. Singular Value Decompositio…
Language ModelingLanguage ModellingLarge Language ModelModel Compression