Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

• URL: http://arxiv.org/abs/2502.01941v2
• Date: Wed, 21 May 2025 10:37:50 GMT
• Title: Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
• Authors: Xiang Liu, Zhenheng Tang, Hong Chen, Peijie Dong, Zeyu Li, Xiuze Zhou, Bo Li, Xuming Hu, Xiaowen Chu,
• Abstract summary: We present a benchmark KVFundaBench to evaluate the effects of KV cache compression across diverse fundamental language models.<n>We propose ShotKV, a novel compression approach that handles prefill and decoding phases while maintaining shot-level semantic coherence.
• Score: 29.510433427184385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates an underexplored challenge in large language models (LLMs): the impact of KV cache compression methods on LLMs' fundamental capabilities. Although existing methods achieve impressive compression ratios on long-context benchmarks, their effects on core model capabilities remain understudied. We present a comprehensive benchmark KVFundaBench to systematically evaluate the effects of KV cache compression across diverse fundamental LLM capabilities, spanning world knowledge, commonsense reasoning, arithmetic reasoning, code generation, safety, and long-context understanding and generation.Our analysis reveals serval key findings: (1) \textit{Task-Dependent Degradation}; (2) \textit{Model-Type Robustness} (3) \textit{Prompt Length Vulnerability}; (4) \textit{Chunk-Level Superiority}; (5) \textit{Prompt-Gain Sensitivity}; (6) \textit{Long-Context Generation Sensitivity}. Based on our analysis of attention patterns and cross-task compression performance, we propose ShotKV, a novel compression approach that distinctly handles prefill and decoding phases while maintaining shot-level semantic coherence. Empirical results show that ShotKV achieves $9\%$-$18\%$ performance improvements on long-context generation tasks under aggressive compression ratios.

Related papers

• KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding [72.12756830560217]
  Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.<n>Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value cache during inference has emerged as a primary efficiency bottleneck.<n>By down-sampling the Key-Value vector dimensions into a latent space, we can significantly reduce the KV Cache footprint and improve inference speed.
  arXiv  Detail & Related papers  (2025-07-15T12:52:12Z)
• Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs [27.710036447385697]
  We show a fundamental yet previously overlooked asymmetry in KV caches.<n>While adjacent keys receive similar attention weights (local homogeneity), adjacent values demonstrate distinct heterogeneous distributions.<n>This key-value asymmetry reveals a critical limitation in existing compression methods that treat keys and values uniformly.
  arXiv  Detail & Related papers  (2025-06-04T16:10:44Z)
• ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration [81.81027217759433]
  Large language models (LLMs) are often constrained by the excessive memory required to store the Key-Value ( KV) cache.<n>Recent methods have explored reducing the hidden dimensions of the KV cache, but many introduce additional computation through projection layers.<n>We propose ReCalKV, a post-training KV cache compression method that reduces the hidden dimensions of the KV cache.
  arXiv  Detail & Related papers  (2025-05-30T08:49:27Z)
• Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques [14.69396650781309]
  Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. As context length grows, the computational cost of attention increases quadratically with the number of tokens. This paper presents an analysis of various Key-Value (KV) cache compression strategies.
  arXiv  Detail & Related papers  (2025-03-14T19:02:16Z)
• KV-Distill: Nearly Lossless Learnable Context Compression for LLMs [37.0803484148612]
  We introduce KV-Distill, a Transformer compression framework that distills long context KV caches into significantly shorter representations. KV-Distill can be trained as a parameter-efficient adaptor for pretrained models. It can be fine-tuned on domain-specific contexts to reduce lengths by up to 99% while preserving downstream performance.
  arXiv  Detail & Related papers  (2025-03-13T13:15:28Z)
• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV. It features an attention-based metric to signal when the remaining KV cache is unlikely to match the full-cache performance, then halting the pruning process. Our method is easy to integrate within LLM inference, not only optimizing memory space, but also showing reduced inference time compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-24T06:33:39Z)
• Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal [56.307484956135355]
  CODiff is a compression-aware one-step diffusion model for JPEG artifact removal. We propose a dual learning strategy that combines explicit and implicit learning. Results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics.
  arXiv  Detail & Related papers  (2025-02-14T02:46:27Z)
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference [24.48498639513474]
  We introduce ChunkKV, grouping the tokens in a chunk as a basic compressing unit.<n>ChunkKV exhibits higher similarity in the preserved indices across different layers.<n>We evaluate ChunkKV on cutting-edge long-context benchmarks including LongBench and Needle-In-A-HayStack, as well as the GSM8K and JailbreakV in-context learning benchmark.
  arXiv  Detail & Related papers  (2025-02-01T03:49:47Z)
• More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression [71.42818367729573]
  In large language models (LLMs), the memory usage of KV cache has become a critical bottleneck during inference.<n>The mainstream KV compression methods, including KV pruning and KV quantization, primarily focus on either token or precision dimension separately.<n>In this paper, we comprehensively investigate the token-precision trade-off in KV cache compression.
  arXiv  Detail & Related papers  (2024-12-17T09:20:31Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective.<n>We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids.<n>Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)
• KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing [58.29726147780976]
  We propose a plug-and-play method called textit KVSharer, which shares the KV cache between layers to achieve layer-wise compression. Experiments show that textit KVSharer can reduce KV cache computation by 30%, thereby lowering memory consumption. We verify that textit KVSharer is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
  arXiv  Detail & Related papers  (2024-10-24T08:06:41Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios [13.144156413032896]
  We introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression. We show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%.
  arXiv  Detail & Related papers  (2024-09-16T17:36:50Z)
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling [53.08975547824068]
  We investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information through Pyramidal Information Funneling where attention is scattering widely in lower layers. Motivated by these insights, we developed Pyramid KV, a novel and effective KV cache compression method.
  arXiv  Detail & Related papers  (2024-06-04T07:51:30Z)
• Activations and Gradients Compression for Model-Parallel Training [85.99744701008802]
  We study how simultaneous compression of activations and gradients in model-parallel distributed training setup affects convergence. We find that gradients require milder compression rates than activations. Experiments also show that models trained with TopK perform well only when compression is also applied during inference.
  arXiv  Detail & Related papers  (2024-01-15T15:54:54Z)
• What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression [68.82486784654817]
  We study two popular model compression techniques including knowledge distillation and pruning. We show that compressed models are significantly less robust than their PLM counterparts on adversarial test sets. We develop a regularization strategy for model compression based on sample uncertainty.
  arXiv  Detail & Related papers  (2021-10-16T00:20:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.