TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

• URL: http://arxiv.org/abs/2410.05076v1
• Date: Mon, 7 Oct 2024 14:30:27 GMT
• Title: TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
• Authors: Lijie Yang, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia,
• Abstract summary: Large language models (LLMs) have driven significant advancements across diverse NLP tasks. This paper introduces TidalDecode, a system for fast and accurate LLM decoding through position persistent sparse attention.
• Score: 7.4088392854630625
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer architectures intensifies the memory constraints, particularly during the decoding phase, creating a significant bottleneck. Existing sparse attention mechanisms designed to address this bottleneck have two limitations: (1) they often fail to reliably identify the most relevant tokens for attention, and (2) they overlook the spatial coherence of token selection across consecutive Transformer layers, which can lead to performance degradation and substantial overhead in token selection. This paper introduces TidalDecode, a simple yet effective algorithm and system for fast and accurate LLM decoding through position persistent sparse attention. TidalDecode leverages the spatial coherence of tokens selected by existing sparse attention methods and introduces a few token selection layers that perform full attention to identify the tokens with the highest attention scores, while all other layers perform sparse attention with the pre-selected tokens. This design enables TidalDecode to substantially reduce the overhead of token selection for sparse attention without sacrificing the quality of the generated results. Evaluation on a diverse set of LLMs and tasks shows that TidalDecode closely matches the generative performance of full attention methods while reducing the LLM decoding latency by up to 2.1x.

Related papers

• Order-agnostic Identifier for Large Language Model-based Generative Recommendation [94.37662915542603]
  Items are assigned identifiers for Large Language Models (LLMs) to encode user history and generate the next item. Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings. We propose SETRec, which leverages semantic tokenizers to obtain order-agnostic multi-dimensional tokens.
  arXiv  Detail & Related papers  (2025-02-15T15:25:38Z)
• Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity [24.118503938098307]
  Existing methods, including selective token retention and window-based attention, improve efficiency but risk discarding important tokens needed for future text generation. We propose an approach that enhances LLM efficiency without token loss by reducing the memory and computational load of less important tokens, rather than discarding them.
  arXiv  Detail & Related papers  (2024-12-03T08:29:27Z)
• 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)
• TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection [23.20856449846164]
  TokenSelect is a model-agnostic, training-free method for efficient and accurate long-context inference. A comprehensive evaluation of TokenSelect demonstrates up to 23.84x speedup in attention and up to 2.28x acceleration in end-to-end latency.
  arXiv  Detail & Related papers  (2024-11-05T07:56:24Z)
• FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction [11.146015814220858]
  We propose FiRST, an algorithm that reduces latency by using layer-specific routers to select a subset of transformer layers adaptively for each input sequence. FiRST preserves compatibility with KV caching enabling faster inference while being quality-aware. Our approach reveals that input adaptivity is critical - indeed, different task-specific middle layers play a crucial role in evolving hidden representations depending on tasks.
  arXiv  Detail & Related papers  (2024-10-16T12:45:35Z)
• 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)
• Efficient Inference for Large Language Model-based Generative Recommendation [78.38878421030522]
  Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly. Applying Speculative Decoding (SD) to generative recommendation presents unique challenges due to the requirement of generating top-K items. We propose an alignment framework named AtSpeed, which presents the AtSpeed-S optimization objective for top-K alignment under the strict top-K verification.
  arXiv  Detail & Related papers  (2024-10-07T16:23:36Z)
• FlexAttention for Efficient High-Resolution Vision-Language Models [67.82024785677801]
  We propose FlexAttention, a flexible attention mechanism for efficient high-resolution vision-language models. A high-resolution image is encoded both as high-resolution tokens and low-resolution tokens, where only the low-resolution tokens and a few selected high-resolution tokens are utilized. Experiments on multimodal benchmarks prove that our FlexAttention outperforms existing high-resolution VLMs.
  arXiv  Detail & Related papers  (2024-07-29T17:59:05Z)
• Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference [59.91176945361035]
  We introduce Visual Tokens Withdrawal (VTW), a plug-and-play module to boost MLLMs for rapid inference. VTW strategically withdraws vision tokens at a certain layer, enabling only text tokens to engage in subsequent layers. Our approach can cut computational overhead by over 40% across diverse multimodal tasks while maintaining performance.
  arXiv  Detail & Related papers  (2024-05-09T14:38:53Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding [90.77031668988661]
  Cluster-Former is a novel clustering-based sparse Transformer to perform attention across chunked sequences. The proposed framework is pivoted on two unique types of Transformer layer: Sliding-Window Layer and Cluster-Former Layer. Experiments show that Cluster-Former achieves state-of-the-art performance on several major QA benchmarks.
  arXiv  Detail & Related papers  (2020-09-13T22:09:30Z)

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.