Multi-matrix Factorization Attention

• URL: http://arxiv.org/abs/2412.19255v2
• Date: Tue, 14 Jan 2025 05:48:07 GMT
• Title: Multi-matrix Factorization Attention
• Authors: Jingcheng Hu, Houyi Li, Yinmin Zhang, Zili Wang, Shuigeng Zhou, Xiangyu Zhang, Heung-Yeung Shum, Daxin Jiang,
• Abstract summary: We propose Multi-matrix Factorization Attention (MFA) and MFA-Key-Reuse (MFA-KR) MFA enhances model capacity by efficiently scaling up both the number and dimension of attention heads. MFA-KR further reduces memory requirements by repurposing the key cache as value.
• Score: 59.10039136733939
• License:
• Abstract: We propose novel attention architectures, Multi-matrix Factorization Attention (MFA) and MFA-Key-Reuse (MFA-KR). Existing variants for standard Multi-Head Attention (MHA), including SOTA methods like MLA, fail to maintain as strong performance under stringent Key-Value cache (KV cache) constraints. MFA enhances model capacity by efficiently scaling up both the number and dimension of attention heads through low-rank matrix factorization in the Query-Key (QK) circuit. Extending MFA, MFA-KR further reduces memory requirements by repurposing the key cache as value through value projection re-parameterization. MFA's design enables strong model capacity when working under tight KV cache budget, while MFA-KR is suitable for even harsher KV cache limits with minor performance trade-off. Notably, in our extensive and large-scale experiments, the proposed architecture outperforms MLA and performs comparably to MHA, while reducing KV cache usage by up to 56% and 93.7%, respectively.

Related papers

• 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)
• TransMLA: Multi-Head Latent Attention Is All You Need [22.354283924006786]
  We introduce Multi-head Latent Attention (MLA) to solve communication bottlenecks in large language models. We show that GQA can always be represented by MLA while maintaining the same KV cache overhead, but the converse does not hold. We plan to develop MLA-specific inference acceleration techniques to preserve low latency in transformed models.
  arXiv  Detail & Related papers  (2025-02-11T18:20:18Z)
• 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)
• 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)
• 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)
• Reducing Transformer Key-Value Cache Size with Cross-Layer Attention [19.796549720022554]
  We show that it is possible to take Multi-Query Attention a step further by also sharing key and value heads between adjacent layers. We find that it is possible to reduce the size of the KV cache by another 2x while maintaining nearly the same accuracy as unmodified MQA.
  arXiv  Detail & Related papers  (2024-05-21T17:59:29Z)
• 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)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization [67.74400574357472]
  LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision. Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods.
  arXiv  Detail & Related papers  (2024-01-31T18:58:14Z)

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.