VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
- URL: http://arxiv.org/abs/2410.23317v1
- Date: Tue, 29 Oct 2024 20:04:34 GMT
- Title: VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
- Authors: Dezhan Tu, Danylo Vashchilenko, Yuzhe Lu, Panpan Xu,
- Abstract summary: Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks.
Key-Value (KV) cache encodes long visual contexts, such as images or videos.
Existing KV cache compression methods are effective for Large Language Models (LLMs)
We propose a novel KV cache compression recipe tailored for accelerating VLM inference.
- Score: 7.463830743649754
- License:
- Abstract: Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as images or videos. While existing KV cache compression methods are effective for Large Language Models (LLMs), directly migrating them to VLMs yields suboptimal accuracy and speedup. To bridge the gap, we propose VL-Cache, a novel KV cache compression recipe tailored for accelerating VLM inference. In this paper, we first investigate the unique sparsity pattern of VLM attention by distinguishing visual and text tokens in prefill and decoding phases. Based on these observations, we introduce a layer-adaptive sparsity-aware cache budget allocation method that effectively distributes the limited cache budget across different layers, further reducing KV cache size without compromising accuracy. Additionally, we develop a modality-aware token scoring policy to better evaluate the token importance. Empirical results on multiple benchmark datasets demonstrate that retaining only 10% of KV cache achieves accuracy comparable to that with full cache. In a speed benchmark, our method accelerates end-to-end latency of generating 100 tokens by up to 2.33x and speeds up decoding by up to 7.08x, while reducing the memory footprint of KV cache in GPU by 90%.
Related papers
- FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation [4.856070170902535]
Large language models (LLMs) excel at handling long-context sequences.
They require substantial key-value ( KV) caches to store contextual information.
FastKV is a KV cache compression method designed to enhance latency for long-context sequences.
arXiv Detail & Related papers (2025-02-03T05:25:09Z) - 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) - ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression [10.003118268356017]
Long context poses significant challenges for inference efficiency.
We introduce ClusterKV, which recalls tokens at the granularity of semantic clusters.
Experiment results show that ClusterKV attains negligible accuracy loss across various tasks with 32k context lengths.
arXiv Detail & Related papers (2024-12-04T10:58:27Z) - KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing [58.29726147780976]
We propose a plug-and-play method called textit KVSharer, which shares the KV cache between layers to achieve layer-wise compression.
Experiments show that textit KVSharer can reduce KV cache computation by 30%, thereby lowering memory consumption.
We verify that textit KVSharer is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
arXiv Detail & Related papers (2024-10-24T08:06:41Z) - 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) - Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models.
We propose an importance-driven cache merging strategy to prune redundancy caches.
For instruction encoding, we utilize the frequency to evaluate the importance of caches.
Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
arXiv Detail & Related papers (2024-07-25T15:29:05Z) - 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) - Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs [82.08922896531618]
We introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs)
We conduct targeted profiling to discern the intrinsic structure of attention modules.
Based on the recognized structure, we then construct the KV cache in an adaptive manner: evicting long-range contexts on attention heads emphasizing local contexts, discarding non-special tokens on attention heads centered on special tokens, and only employing the standard KV cache for attention heads that broadly attend to all tokens.
arXiv Detail & Related papers (2023-10-03T05:17:08Z)
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.