Layer-Condensed KV Cache for Efficient Inference of Large Language Models

• URL: http://arxiv.org/abs/2405.10637v2
• Date: Tue, 4 Jun 2024 00:08:10 GMT
• Title: Layer-Condensed KV Cache for Efficient Inference of Large Language Models
• Authors: Haoyi Wu, Kewei Tu,
• Abstract summary: We propose a novel method that only computes and caches the KVs of a small number of layers. Our method achieves up to 26$times$ higher throughput than standard transformers.
• Score: 44.24593677113768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the transformer architecture consumes a significant amount of memory, especially when the number of layers is large for deep language models. In this paper, we propose a novel method that only computes and caches the KVs of a small number of layers, thus significantly saving memory consumption and improving inference throughput. Our experiments on large language models show that our method achieves up to 26$\times$ higher throughput than standard transformers and competitive performance in language modeling and downstream tasks. In addition, our method is orthogonal to existing transformer memory-saving techniques, so it is straightforward to integrate them with our model, achieving further improvement in inference efficiency. Our code is available at https://github.com/whyNLP/LCKV.

Related papers

• Tensor Product Attention Is All You Need [54.40495407154611]
  Product Attention (TPA) is a novel attention mechanism that uses tensor decompositions to represent queries, keys, and values compactly. TPA achieves improved model quality alongside memory efficiency. We introduce the ProducT ATTion Transformer (T6), a new model architecture for sequence modeling.
  arXiv  Detail & Related papers  (2025-01-11T03:37:10Z)
• CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation [63.65323577445951]
  We propose a novel approach called Cache Sparse Representation (CSR) CSR transforms the dense Key-Value cache tensor into sparse indexes and weights, offering a more memory-efficient representation during LLM inference. Our experiments demonstrate CSR achieves performance comparable to state-of-the-art KV cache quantization algorithms.
  arXiv  Detail & Related papers  (2024-12-16T13:01:53Z)
• 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)
• A Method for Building Large Language Models with Predefined KV Cache Capacity [11.710667043543545]
  The Bounded-Cache Transformer (BCT) addresses the excessive memory consumption issue in traditional KV caches. By dynamically updating the key-value vector sequences, the BCT achieves efficient inference within limited cache capacity. Experimental results demonstrate that the BCT significantly reduces memory usage while maintaining the model's inference quality.
  arXiv  Detail & Related papers  (2024-11-24T11:30:00Z)
• InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management [0.5899781520375794]
  Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. serving inference for generating long contents poses a challenge due to the enormous memory footprint of the transient state. InfiniGen is a novel KV cache management framework tailored for long-text generation.
  arXiv  Detail & Related papers  (2024-06-28T07:41:26Z)
• 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)
• A Survey on Transformer Compression [84.18094368700379]
  Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV) Model compression methods reduce the memory and computational cost of Transformer. This survey provides a comprehensive review of recent compression methods, with a specific focus on their application to Transformer-based models.
  arXiv  Detail & Related papers  (2024-02-05T12:16:28Z)
• Compressed Context Memory For Online Language Model Interaction [39.72054168889216]
  This paper presents a context key/value compression method for Transformer language models in online scenarios. As the context lengthens, the attention process demands increasing memory and computations, which in turn reduces the throughput of the language model. We propose a compressed context memory system that continually compresses the accumulating attention key/value pairs into a compact memory space.
  arXiv  Detail & Related papers  (2023-12-06T10:50:43Z)
• Direction is what you need: Improving Word Embedding Compression in Large Language Models [7.736463504706344]
  This paper presents a novel loss objective to compress token embeddings in Transformer-based models by leveraging an AutoEncoder architecture. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity.
  arXiv  Detail & Related papers  (2021-06-15T14:28:00Z)

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.