WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization

• URL: http://arxiv.org/abs/2605.02262v1
• Date: Mon, 04 May 2026 06:17:13 GMT
• Title: WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
• Abstract summary: Existing methods propose mixed-precision quantization to the key-value (KV) cache in video language models (VLMs)<n>This paper introduces a novel approach called WindowQuant, which employs window-adaptive mixed-precision quantization to optimize the KV cache.<n> WindowQuant outperforms state-of-the-art VLM models and KV cache quantization methods on various datasets.
• Score: 50.768455096160984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in VLMs based on token granularity, which is time-consuming in the search process and hardware inefficient during computation. This paper introduces a novel approach called WindowQuant, which employs window-adaptive mixed-precision quantization to optimize the KV cache. WindowQuant consists of two modules: window-level quantization search and window-level KV cache computation. Window-level quantization search quickly determines the optimal bit-width configuration of the KV cache windows based on the similarity scores between the corresponding visual token windows and the text prompt, maintaining the model accuracy. Furthermore, window-level KV cache computation reorders the KV cache windows before quantization, avoiding the hardware inefficiency caused by mixed-precision quantization in inference computation. Extensive experiments demonstrate that WindowQuant outperforms state-of-the-art VLM models and KV cache quantization methods on various datasets.

Related papers

• Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference [24.184349246524587]
  Cocktail employs chunk-adaptive mixed-precision quantization to optimize the KV cache.<n>Chunk-level quantization search determines the optimal bitwidth configuration of the KV cache chunks.<n>Cocktail outperforms state-of-the-art KV cache quantization methods on various models and datasets.
  arXiv  Detail & Related papers  (2025-03-30T03:20:34Z)
• WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference [9.572076809796448]
  We propose a novel task-adaptive KV cache window selection method, WindowKV.<n>We show that WindowKV maintains a performance comparable to full KV cache retention while using only 12% of the original KV cache.<n>Our method also achieves state-of-the-art results in the Needle-in-a-Haystack evaluation, highlighting its effectiveness and robustness.
  arXiv  Detail & Related papers  (2025-03-23T03:36:52Z)
• CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs [45.77132019859689]
  CalibQuant is a visual quantization strategy that drastically reduces both memory and computational overhead.<n>We achieve a 10x throughput increase on InternVL models.
  arXiv  Detail & Related papers  (2025-02-15T05:08:01Z)
• KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference [40.97781175723418]
  KV cache quantization can improve Large Language Models inference throughput and latency in long contexts.<n>Current methods have three unsolved issues: overlooking layer-wise sensitivity to KV cache quantization, high overhead of online fine-grained decision-making, and low flexibility to different LLMs and constraints.<n>We propose a simple yet effective framework KVTuner to adaptively search for the optimal hardware-friendly layer-wise KV quantization precision pairs for coarse-grained KV cache.
  arXiv  Detail & Related papers  (2025-02-06T15:26:26Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective.<n>We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids.<n>Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)
• 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)
• SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models [43.22490117833939]
  SKVQ stands for sliding-window KV cache quantization. S KVQ rearranges the channels of the KV cache in order to improve the similarity of channels in quantization groups. It is possible to process context lengths of up to 1M on an 80GB memory GPU for a 7b model and up to 7 times faster decoding.
  arXiv  Detail & Related papers  (2024-05-10T03:06:24Z)
• 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)
• 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)
• 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.<n> Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision.<n>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.