Pith. sign in

REVIEW 3 cited by

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.15021 v1 pith:LV63QY2T submitted 2025-01-25 cs.CL

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models

classification cs.CL
keywords akvq-vlquantizationmultimodalattentionmodelsattention-awarecachesmemory
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV quantization methods for Large Language Models (LLMs) may alleviate these issues but overlook the attention saliency differences of multimodal tokens, resulting in suboptimal performance. In this paper, we investigate the attention-aware token saliency patterns in VLM and propose AKVQ-VL. AKVQ-VL leverages the proposed Text-Salient Attention (TSA) and Pivot-Token-Salient Attention (PSA) patterns to adaptively allocate bit budgets. Moreover, achieving extremely low-bit quantization requires effectively addressing outliers in KV tensors. AKVQ-VL utilizes the Walsh-Hadamard transform (WHT) to construct outlier-free KV caches, thereby reducing quantization difficulty. Evaluations of 2-bit quantization on 12 long-context and multimodal tasks demonstrate that AKVQ-VL maintains or even improves accuracy, outperforming LLM-oriented methods. AKVQ-VL can reduce peak memory usage by 2.13x, support up to 3.25x larger batch sizes and 2.46x throughput.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

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

    cs.CV 2026-05 unverdicted novelty 6.0

    WindowQuant performs window-adaptive mixed-precision KV cache quantization guided by similarity to the text prompt, with reordering to enable efficient inference in VLMs.

  2. KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy

    cs.CV 2026-05 unverdicted novelty 5.0

    KVCapsule compresses KV cache in VLMs by 60% to deliver up to 2x higher tokens-per-second and 2.4x memory reduction with negligible accuracy loss.

  3. SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

    cs.LG 2026-02 conditional novelty 5.0

    SnapMLA achieves up to 1.91x higher throughput in long-output MLA decoding using FP8 quantization and specialized kernels while keeping benchmark quality near the BF16 baseline.