Beyond KV Caching: Shared Attention for Efficient LLMs

• URL: http://arxiv.org/abs/2407.12866v1
• Date: Sat, 13 Jul 2024 07:23:07 GMT
• Title: Beyond KV Caching: Shared Attention for Efficient LLMs
• Authors: Bingli Liao, Danilo Vasconcellos Vargas,
• Abstract summary: This paper introduces a novel Shared Attention (SA) mechanism to enhance the efficiency of large language models (LLMs) Our approach utilizes the isotropic tendencies of attention distributions observed in advanced LLMs post-pretraining to reduce both the computational flops and the size of the KV cache required during inference. Our findings suggest that SA not only conserves computational resources but also maintains robust model performance, thereby facilitating the deployment of more efficient LLMs in resource-constrained environments.
• Score: 5.801044612920816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant computational and memory resources due to the necessity of recalculating and storing attention weights across different layers. This paper introduces a novel Shared Attention (SA) mechanism, designed to enhance the efficiency of LLMs by directly sharing computed attention weights across multiple layers. Unlike previous methods that focus on sharing intermediate Key-Value (KV) caches, our approach utilizes the isotropic tendencies of attention distributions observed in advanced LLMs post-pretraining to reduce both the computational flops and the size of the KV cache required during inference. We empirically demonstrate that implementing SA across various LLMs results in minimal accuracy loss on standard benchmarks. Our findings suggest that SA not only conserves computational resources but also maintains robust model performance, thereby facilitating the deployment of more efficient LLMs in resource-constrained environments.

Related papers

• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs. Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference [11.73134417321505]
  We propose AirCache, a novel KV cache compression method aimed at accelerating LVLMs inference. We show that our method achieves comparable performance to the full cache while retaining only 10% of visual KV cache.
  arXiv  Detail & Related papers  (2025-03-31T11:13:18Z)
• Cost-Optimal Grouped-Query Attention for Long-Context LLMs [64.90662568387683]
  Building effective Transformer-based large language models (LLMs) has recently become a research focus. We compare models with different parameter sizes, context lengths, and attention head configurations in terms of model performance, computational cost, and memory cost. Our studies show that, when processing sufficiently long sequences, a larger model with fewer attention heads can achieve a lower loss while incurring lower computational and memory costs.
  arXiv  Detail & Related papers  (2025-03-12T17:50:42Z)
• Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs [74.74225314708225]
  Multi-head Latent Attention (MLA) is an innovative architecture designed to ensure efficient and economical inference. This paper proposes the first data-efficient fine-tuning method for transitioning from Multi-Head Attention to MLA.
  arXiv  Detail & Related papers  (2025-02-20T18:50:42Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge. Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities. LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands. We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• eFedLLM: Efficient LLM Inference Based on Federated Learning [1.6179784294541053]
  Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI) This paper introduces an effective approach that enhances the operational efficiency and affordability of LLM inference.
  arXiv  Detail & Related papers  (2024-11-24T22:50:02Z)
• Anchor Attention, Small Cache: Code Generation with Large Language Models [15.94784908771546]
  Current practices in NLP often use sparse attention which may, unfortunately, lead to substantial inaccuracies, or hallucinations, in code generation tasks. We propose a novel approach, AnchorCoder, which features token-wise anchor attention designed to extract and compress contextual information. It can consistently achieve a significant (at least 70%) reduction in KV cache requirements, while preserving the majority of model's performance.
  arXiv  Detail & Related papers  (2024-11-11T02:47:05Z)
• A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs [74.35290684163718]
  A primary challenge in large language model (LLM) development is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by leveraging a small language model (SLM)
  arXiv  Detail & Related papers  (2024-10-24T14:31:52Z)
• Reprogramming Foundational Large Language Models(LLMs) for Enterprise Adoption for Spatio-Temporal Forecasting Applications: Unveiling a New Era in Copilot-Guided Cross-Modal Time Series Representation Learning [0.0]
  patio-temporal forecasting plays a crucial role in various sectors such as transportation systems, logistics, and supply chain management. We introduce a hybrid approach that combines the strengths of open-source large and small-scale language models (LLMs and LMs) with traditional forecasting methods.
  arXiv  Detail & Related papers  (2024-08-26T16:11:53Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• 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)
• Mamba-PTQ: Outlier Channels in Recurrent Large Language Models [49.1574468325115]
  We show that Mamba models exhibit the same pattern of outlier channels observed in attention-based LLMs. We show that the reason for the difficulty of quantizing SSMs is caused by activation outliers, similar to those observed in transformer-based LLMs.
  arXiv  Detail & Related papers  (2024-07-17T08:21:06Z)
• Effectively Compress KV Heads for LLM [28.0801697946958]
  We propose a novel approach for compressing Key-Value ( KV) caches. Our method can compress half or even three-quarters of KV heads while maintaining performance comparable to the original LLMs.
  arXiv  Detail & Related papers  (2024-06-11T08:37:33Z)
• Attention is Naturally Sparse with Gaussian Distributed Input [8.602260591839318]
  This study presents a rigorous theoretical analysis of the sparsity in attention scores within Large Language Models (LLMs) Our main contribution lies in providing a detailed theoretical examination of how sparsity manifests in attention mechanisms, offering insights into the potential trade-offs between computational savings and model effectiveness.
  arXiv  Detail & Related papers  (2024-04-03T12:37:34Z)
• MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT [87.4910758026772]
  "Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. This paper explores the "less is more" paradigm by addressing the challenge of designing accurate yet efficient Small Language Models (SLMs) for resource constrained devices.
  arXiv  Detail & Related papers  (2024-02-26T18:59:03Z)
• WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More [55.0856305773081]
  Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers.
  arXiv  Detail & Related papers  (2024-02-19T11:33:21Z)

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.