KV-Distill: Nearly Lossless Learnable Context Compression for LLMs

• URL: http://arxiv.org/abs/2503.10337v1
• Date: Thu, 13 Mar 2025 13:15:28 GMT
• Title: KV-Distill: Nearly Lossless Learnable Context Compression for LLMs
• Authors: Vivek Chari, Guanghui Qin, Benjamin Van Durme,
• Abstract summary: We introduce KV-Distill, a Transformer compression framework that distills long context KV caches into significantly shorter representations.<n> KV-Distill can be trained as a parameter-efficient adaptor for pretrained models.<n>It can be fine-tuned on domain-specific contexts to reduce lengths by up to 99% while preserving downstream performance.
• Score: 37.0803484148612
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV cache-account for a large portion of GPU memory usage and scale linearly with context length. We introduce KV-Distill, a Transformer compression framework that distills long context KV caches into significantly shorter representations in a question-independent fashion. KV-Distill can be trained as a parameter-efficient adaptor for pretrained models, and enables the compression of arbitrary spans of a context while preserving pre-trained model capabilities. We treat a compressed-uncompressed cache as a student-teacher pairing and apply a KL-type divergence to match the generated outputs. KV-Distill outperforms other compression techniques in worst-case extractive tasks and approaches uncompressed performance in long context question answering and summarization, and it can be fine-tuned on domain-specific contexts to reduce lengths by up to 99% while preserving downstream performance. We demonstrate the generalizability of KV-Distill across various model sizes and architectures.

Related papers

• FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension [19.80328834174459]
  Existing methods suffer from performance degradation when extending to longer contexts. Our method exploits a key observation: in the frequency domain, the energy distribution of the KV cache is primarily concentrated in low-frequency components. We propose an efficient compression technique, FreqKV, that iteratively compresses the increasing KV cache to a fixed size in the frequency domain.
  arXiv  Detail & Related papers  (2025-05-01T14:53:12Z)
• Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs [6.222287867011644]
  We propose MorphKV, an inference-time technique that maintains a constant-sized KV cache while preserving accuracy.<n>Unlike retention or lossy compression, MorphKV iteratively refines the KV cache via lightweight updates guided by attention patterns of recent tokens.<n>Our studies show 52.9$%$ memory savings and 18.2$%$ higher accuracy on average compared to state-of-the-art prior works.
  arXiv  Detail & Related papers  (2025-03-02T18:12:50Z)
• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV.<n>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.<n>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)
• 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)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• LoCoCo: Dropping In Convolutions for Long Context Compression [77.26610232994508]
  This paper presents a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo) LoCoCo employs only a fixed-size Key-Value ( KV) cache, and can enhance efficiency in both inference and fine-tuning stages.
  arXiv  Detail & Related papers  (2024-06-08T01:35:11Z)
• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs [82.08922896531618]
  We introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs) We conduct targeted profiling to discern the intrinsic structure of attention modules. Based on the recognized structure, we then construct the KV cache in an adaptive manner: evicting long-range contexts on attention heads emphasizing local contexts, discarding non-special tokens on attention heads centered on special tokens, and only employing the standard KV cache for attention heads that broadly attend to all tokens.
  arXiv  Detail & Related papers  (2023-10-03T05:17:08Z)
• Once-for-All Sequence Compression for Self-Supervised Speech Models [62.60723685118747]
  We introduce a once-for-all sequence compression framework for self-supervised speech models. The framework is evaluated on various tasks, showing marginal degradation compared to the fixed compressing rate variants. We also explore adaptive compressing rate learning, demonstrating the ability to select task-specific preferred frame periods without needing a grid search.
  arXiv  Detail & Related papers  (2022-11-04T09:19:13Z)

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.