GTA: Grouped-head latenT Attention

• URL: http://arxiv.org/abs/2506.17286v2
• Date: Wed, 23 Jul 2025 05:57:32 GMT
• Title: GTA: Grouped-head latenT Attention
• Authors: Luoyang Sun, Cheng Deng, Jiwen Jiang, Xinjian Wu, Haifeng Zhang, Lei Chen, Lionel Ni, Jun Wang,
• Abstract summary: A critical bottleneck arises as KV cache and attention computations scale rapidly with text length.<n>We propose textbfGrouped-Head LatentextbfT textbfAttention (GTA), a novel attention mechanism that reduces memory usage and computational complexity while maintaining performance.<n>GTA cuts attention FLOPs by up to emph62.5% versus Grouped-Query Attention and shrink the KV cache by up to emph70%, all while avoiding the extra overhead of Multi-Head Latent Attention
• Score: 44.19575886935378
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and attention computations scale rapidly with text length, challenging deployment on hardware with limited computational and memory resources. We observe that attention mechanisms exhibit substantial redundancy, since the KV cache can be significantly compressed and attention maps across heads display high similarity, revealing that much of the computation and storage is unnecessary. Leveraging these insights, we propose \textbf{G}rouped-Head Laten\textbf{T} \textbf{A}ttention (GTA), a novel attention mechanism that reduces memory usage and computational complexity while maintaining performance. GTA comprises two components: (1) a shared attention map mechanism that reuses attention scores across multiple heads, decreasing the key cache size; and (2) a nonlinear value decoder with learned projections that compresses the value cache into a latent space, further cutting memory needs. GTA cuts attention computation FLOPs by up to \emph{62.5\%} versus Grouped-Query Attention and shrink the KV cache by up to \emph{70\%}, all while avoiding the extra overhead of Multi-Head Latent Attention to improve LLM deployment efficiency. Consequently, GTA models achieve a \emph{2x} increase in end-to-end inference speed, with prefill benefiting from reduced computational cost and decoding benefiting from the smaller cache footprint.

Related papers

• ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration [81.81027217759433]
  Large language models (LLMs) are often constrained by the excessive memory required to store the Key-Value ( KV) cache.<n>Recent methods have explored reducing the hidden dimensions of the KV cache, but many introduce additional computation through projection layers.<n>We propose ReCalKV, a post-training KV cache compression method that reduces the hidden dimensions of the KV cache.
  arXiv  Detail & Related papers  (2025-05-30T08:49:27Z)
• CacheFormer: High Attention-Based Segment Caching [0.0]
  We show how to efficiently handle long contexts in transformer-based language models with low perplexity.<n>Our enhancements result in an architecture that outperforms ex-isting SOTA architectures with an average perplexity improvement of 8.5% over similar model sizes.
  arXiv  Detail & Related papers  (2025-04-18T06:34:57Z)
• ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs [7.958429361868486]
  We propose ZSMerge, a dynamic KV cache compression framework for efficient cache management.<n>ZSMerge significantly enhances memory efficiency and inference speed with negligible performance degradation.
  arXiv  Detail & Related papers  (2025-03-13T03:36:03Z)
• Eigen Attention: Attention in Low-Rank Space for KV Cache Compression [9.080678336379528]
  We propose Eigen Attention, which performs the attention operation in a low-rank space, thereby reducing the KV cache memory overhead. We show that Eigen Attention results in up to 40% reduction in KV cache sizes and up to 60% reduction in attention operation latency with minimal drop in performance.
  arXiv  Detail & Related papers  (2024-08-10T22:47:12Z)
• 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.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>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)
• PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference [57.53291046180288]
  Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference. We propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache.
  arXiv  Detail & Related papers  (2024-05-21T06:46:37Z)
• 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)
• DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference [22.684773338989007]
  Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens.<n>Existing inference systems for tree-based applications are inefficient due to improper partitioning of queries and KV cache during attention calculation.<n>We propose DeFT, a hardware-efficient attention algorithm with prefix-aware and load-balanced KV cache partitions.
  arXiv  Detail & Related papers  (2024-03-30T04:34:54Z)
• KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache [67.9776980972508]
  We develop a tuning-free 2bit KV cache quantization algorithm named KIVI. KIVI can enable Llama, Falcon, and Mistral models to maintain almost the same quality while using $mathbf2.6times$ less peak memory.
  arXiv  Detail & Related papers  (2024-02-05T06:06:47Z)

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.