Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

• URL: http://arxiv.org/abs/2407.11550v4
• Date: Sun, 26 Jan 2025 07:29:06 GMT
• Title: Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
• Authors: Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S. Kevin Zhou,
• Abstract summary: Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache. Recent efforts aim to reduce KV cache size by evicting vast non-critical cache elements during runtime. We propose Ada-KV, the first head-wise adaptive budget allocation strategy.
• Score: 19.447729423696096
• License:
• Abstract: Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical cache elements during runtime while preserving generation quality. However, these methods typically allocate compression budgets uniformly across all attention heads, ignoring the unique attention patterns of each head. In this paper, we establish a theoretical loss upper bound between pre- and post-eviction attention output, explaining the optimization target of prior cache eviction methods, while guiding the optimization of adaptive budget allocation. Base on this, we propose {\it Ada-KV}, the first head-wise adaptive budget allocation strategy. It offers plug-and-play benefits, enabling seamless integration with prior cache eviction methods. Extensive evaluations on 13 datasets from Ruler and 16 datasets from LongBench, all conducted under both question-aware and question-agnostic scenarios, demonstrate substantial quality improvements over existing methods.

Related papers

• SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation [28.78295040602572]
  SCOPE is a framework that performs KV cache optimization during the prefill and decoding phases. memory usage and memory transfer are further optimized using adaptive and discontinuous strategies. experiments on LongGenBench show the effectiveness and generalization of SCOPE.
  arXiv  Detail & Related papers  (2024-12-18T09:27:33Z)
• Cross-Self KV Cache Pruning for Efficient Vision-Language Inference [19.062950348441426]
  KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. We propose decomposing attention scores into intra-modality attention (within the same modality) and inter-modality attention (across modalities) Our final training-free method, textbfCross-textbfSelf textbfPruning (CSP), achieves competitive performance compared to models with full KV caches.
  arXiv  Detail & Related papers  (2024-12-05T22:47:17Z)
• PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation [65.36715026409873]
  Key-value (KV) cache, necessitated by the lengthy input and output sequences, notably contributes to the high inference cost. We present PrefixKV, which reframes the challenge of determining KV cache sizes for all layers into the task of searching for the optimal global prefix configuration. Our method achieves the state-of-the-art performance compared with others.
  arXiv  Detail & Related papers  (2024-12-04T15:48:59Z)
• 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. This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference. 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)
• Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
  We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models. We propose an importance-driven cache merging strategy to prune redundancy caches. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
  arXiv  Detail & Related papers  (2024-07-25T15:29:05Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• CORM: Cache Optimization with Recent Message for Large Language Model Inference [57.109354287786154]
  We introduce an innovative method for optimizing the KV cache, which considerably minimizes its memory footprint. CORM, a KV cache eviction policy, dynamically retains essential key-value pairs for inference without the need for model fine-tuning. Our validation shows that CORM reduces the inference memory usage of KV cache by up to 70% with negligible performance degradation across six tasks in LongBench.
  arXiv  Detail & Related papers  (2024-04-24T16:11:54Z)
• QAQ: Quality Adaptive Quantization for LLM KV Cache [3.163526369095745]
  A bottleneck in model deployment emerges due to the linear expansion of the Key-Value cache with the context length. We propose QAQ, a Quality Adaptive Quantization scheme for the KV cache.
  arXiv  Detail & Related papers  (2024-03-07T16:42:37Z)
• 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)

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.