cs.CVNov 19, 2026

Online Temporal Rotations for 2 Bit KV-Cache Quantization in Video Diffusion Transformers

Authors: Ryan Lucas, Petros Prastakos, Rahul Mazumder

Organizations: Operations Research Center, Massachusetts Institute of Technology

Abstract

Video diffusion transformers reuse key--value (KV) caches across denoising steps, which quickly becomes a bottleneck for long video generation. We find that quantizing temporally distant cache vectors leads to a large range and high quantization error, but that nearby video tokens in the KV-cache share a persistent pattern per channel. These patterns also vary across videos, motivating rotations that are adapted to each video's unique cache. We propose Temporal Rotation Quantization (TRQ), a method that rotates frames in the cache that are adjacent in time before quantization. For each block of temporally adjacent cache vectors, TRQ fits an orthogonal transform that maps the block's per-channel means to a vector that is close to a constant across channels. To keep the quantization format lightweight, we parameterize this rotation as a tree of 2×22 \times 2 planar rotations, each stored with only two bits, followed by a fixed Hadamard transform shared across all blocks. The rotations are fit without gradients or changes to model weights, and we prove that a simple greedy fit is globally optimal for our 'mean-flattening' objective. The transforms are fit online for each new video, and we release fused Triton kernels to make this process efficient at inference. At 2-bit precision and matched compression, TRQ improves VBench subject consistency over the state-of-the-art method QVG from 90.38 to 92.02 on LongCat-Video-13B and from 86.33 to 87.61 on HY-WorldPlay-8B, as well as improving other metrics.

Figures & tables

Explore similar work

CardsList
  1. Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion

    May 25, 2026Tuna Tuncer, Felix Becker, Thomas PfeilVideo Diffusion ModelsSelf-Attention

  2. TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation

    Oct 11, 2026Jiahui Hu, Weile Mo, Peiliang Cai +5KV-Cache QuantizationVideo Diffusion Models

  3. QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

    Sep 22, 2026Jiaqi Zhao, Xiaobin Hu, Bo Yin +3KV-Cache CompressionKV-Cache Quantization