Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices

• URL: http://arxiv.org/abs/2410.01805v2
• Date: Thu, 30 Jan 2025 13:07:37 GMT
• Title: Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
• Authors: Yuxiang Huang, Binhang Yuan, Xu Han, Chaojun Xiao, Zhiyuan Liu,
• Abstract summary: Locret is first framework to create an eviction policy compatible with chunked prefill.<n>We show that Locret achieves up to 20x of KV cache compression ratio within less than 10% performance loss.<n>We also show that Locret achieves 128K+ long-context inference on a single NVIDIA 4090 GPU without compromising generation quality.
• Score: 30.690302709678758
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from inefficient compression strategies and limited memory reduction effects, making it difficult for LLMs to conduct long-context inference on consumer-grade devices, especially when inferring long-context stream input. Such obstacles prevent consumer-grade devices from supporting more complex applications, creating challenges for the democratization of LLMs. To overcome this, we propose Locret, the first framework to create an eviction policy compatible with chunked prefill. By evaluating the causal importance of KV cache units by learnable retaining heads, Locret enables precise eviction of cache units, facilitating efficient long-context inference. In our extensive empirical studies, Locret outperforms the recent popular and competitive approaches in terms of memory efficiency and generation quality -- Locret achieves up to 20x of KV cache compression ratio within less than 10% performance loss. Furthermore, Locret achieves 128K+ long-context inference on a single NVIDIA 4090 GPU without compromising generation quality and only costs <1 GPU hour of additional training.

Related papers

• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [58.044803442346115]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive computational complexity and memory overhead during inference.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention via delayed bidirectional sparse caching.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management [27.734106884226005]
  FlowKV is a novel multi-turn isolation mechanism for KV Cache management.<n>It preserves the accumulated compressed KV cache from past turns.<n>It prevents the re-compression of older context and thereby mitigating catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-05-21T10:20:46Z)
• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV. It features an attention-based metric to signal when the remaining KV cache is unlikely to match the full-cache performance, then halting the pruning process. Our method is easy to integrate within LLM inference, not only optimizing memory space, but also showing reduced inference time compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-24T06:33:39Z)
• 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)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings. In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency. We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• MPCache: MPC-Friendly KV Cache Eviction for Efficient Private Large Language Model Inference [5.1206021159434805]
  MPCache is built on the observation that historical tokens in a long sequence may have different effects on the downstream decoding. MPCache consistently outperforms prior-art KV cache eviction baselines across different LLM generation tasks.
  arXiv  Detail & Related papers  (2025-01-12T13:18:04Z)
• ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference [25.638980944695728]
  ShadowKV is an efficient long-context large language models (LLMs) inference system. It stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. It can support up to 6$times$ larger batch sizes and boost throughput by up to 3.04$times$ on an A100 GPU.
  arXiv  Detail & Related papers  (2024-10-28T19:08:12Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference [10.115950753431528]
  Large Language Models (LLMs) are a significant milestone in generative AI. The increasing context length and batch size in offline LLM inference escalates the memory requirement of the key-value (KV) cache. Several cost-effective solutions leverage host memory or optimized to reduce storage costs for offline inference scenarios. We propose InstInfer, which offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs) InstInfer improves throughput for long-sequence inference by
  arXiv  Detail & Related papers  (2024-09-08T06:06:44Z)
• NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time [44.89402186438295]
  Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. We propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase.
  arXiv  Detail & Related papers  (2024-08-07T10:31:07Z)
• 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)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks [21.815661269986425]
  We propose a novel KV cache merging approach, called KVMerger, to achieve adaptive KV cache compression for long-context tasks. Our approach is inspired by the intriguing observation that key states exhibit high similarity at the token level within a single sequence. We conduct extensive experiments to demonstrate the effectiveness of KVMerger for long-context tasks under constrained memory budgets.
  arXiv  Detail & Related papers  (2024-07-11T12:50:42Z)
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling [53.08975547824068]
  We investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information through Pyramidal Information Funneling where attention is scattering widely in lower layers. Motivated by these insights, we developed Pyramid KV, a novel and effective KV cache compression method.
  arXiv  Detail & Related papers  (2024-06-04T07:51:30Z)
• MiniCache: KV Cache Compression in Depth Dimension for Large Language Models [48.03117580340151]
  Key-Value ( KV) cache stores key-value states of previously generated tokens. The size of the KV cache grows linearly with sequence length, posing challenges for applications requiring long context input and extensive sequence generation. We present a simple yet effective approach, called MiniCache, to compress the KV cache across layers from a novel depth perspective.
  arXiv  Detail & Related papers  (2024-05-23T09:43:52Z)
• 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.