paper-with-me

홈 › Papers

KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs

2026-02-05 · Jian Chen, Zhuoran Wang, Jiayu Qin, Ming Li, Meng Wang, Changyou Chen, Yin Chen, Qizhen Weng, Yirui Liu arxiv

Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly saturate GPU memory bandwidth. Recent work has explored KV-cache compression, yet most approaches neglect the data-dependent nature of kv-caches and their variation across layers. We introduce KV-CoRE KV-cache Compressibility by Rank Evaluation), an SVD-based method for quantifying the data-dependent low-rank compressibility of kv-caches. KV-CoRE computes the optimal low-rank approximation under the Frobenius norm and, being gradient-free and incremental, enables efficient dataset-level, layer-wise evaluation. Using this method, we analyze multiple models and datasets spanning five English domains and sixteen languages, uncovering systematic patterns that link compressibility to model architecture, training data, and language coverage. As part of this analysis, we employ the Normalized Effective Rank as a metric of compressibility and show that it correlates strongly with performance degradation under compression. Our study establishes a principled evaluation framework and the first large-scale benchmark of kv-cache compressibility in LLMs, offering insights for dynamic, data-aware compression and data-centric model development.

📄 PDF Abstract BibTeX arXiv:2602.05929

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs

2026-05-15 · Hongyu Lu, Feng Zhang, Wenwei Jin, Huanling Hu 외 arxiv

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing atten…

Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility

2025-10-02 · Annan Yu, Danielle C. Maddix, Boran Han, Xiyuan Zhang 외 arxiv

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the …

Compressibility Measures for Affinely Singular Random Vectors

2020-01-12 · Mohammad-Amin Charusaie, Arash Amini, Stefano Rini

There are several ways to measure the compressibility of a random measure; they include general approaches such as using the rate-distortion curve, as well as more specific notions, such as the Renyi information dimensio…

Grokking vs. Learning: Same Features, Different Encodings

2025-02-03 · Dmitry Manning-Coe, Jacopo Gliozzi, Alexander G. Stapleton, Edward Hirst 외

Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental differences in the learned models. To do s…

SLORR: Simple and Efficient In-Training Low-Rank Regularization

2026-07-09 · David González-Martínez, Shiwei Liu arxiv

Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss. Existing training-time low-rank regular…