NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

• URL: http://arxiv.org/abs/2408.03675v2
• Date: Thu, 8 Aug 2024 01:20:13 GMT
• Title: NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
• Authors: Yilong Chen, Guoxia Wang, Junyuan Shang, Shiyao Cui, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun, Dianhai Yu, Hua Wu,
• Abstract summary: Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. We propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase.
• Score: 44.89402186438295
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. Despite several works proposing to evict unnecessary tokens from the KV Cache, most of them rely on the biased local statistics of accumulated attention scores and report performance using unconvincing metric like perplexity on inadequate short-text evaluation. In this paper, we propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase. Due to NACL's efficiency, we combine more accurate attention score statistics in PROXY TOKENS EVICTION with the diversified random eviction strategy of RANDOM EVICTION, aiming to alleviate the issue of attention bias and enhance the robustness in maintaining pivotal tokens for long-context modeling tasks. Notably, our method significantly improves the performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 50% with over 95% performance maintenance. The code is available at https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2024-NACL.

Related papers

• Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference [56.71209737306054]
  We propose textbfActQKV, a training-free, textbfActivation-aware approach that dynamically determines probe-textbfQuery and leverages it to retrieve the relevant textbfKV pairs for inference. Experiments on the Long-Bench and $infty$ Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.
  arXiv  Detail & Related papers  (2025-02-19T08:50:44Z)
• 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)
• In-context KV-Cache Eviction for LLMs via Attention-Gate [12.732519329131392]
  The KV-Cache technique has become the standard for the inference of large language models (LLMs) This paper devises a parameterized KV-Cache eviction mechanism, dubbed as Attention-Gate. Attention-Gate accepts the whole context as input and yields eviction flags for each token to realize in-context eviction.
  arXiv  Detail & Related papers  (2024-10-15T05:01:19Z)
• ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification [29.163757099307553]
  The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase. We present ZipVL, an efficient inference framework designed for LVLMs through a dynamic ratio allocation strategy of important tokens.
  arXiv  Detail & Related papers  (2024-10-11T07:24:21Z)
• 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)
• Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks [21.815661269986425]
  We propose a novel KV cache merging approach, called KVMerger, to achieve adaptive KV cache compression for long-context tasks. Our approach is inspired by the intriguing observation that key states exhibit high similarity at the token level within a single sequence. We conduct extensive experiments to demonstrate the effectiveness of KVMerger for long-context tasks under constrained memory budgets.
  arXiv  Detail & Related papers  (2024-07-11T12:50:42Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens. Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• 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)

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.