arXiv Computer Vision
NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Oct 12
CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
CORAL-KV is a new framework for compressing the key‑value (KV) cache used by autoregressive video diffusion models. It predicts keys and values across cache layers using block‑diagonal‑plus‑low‑rank (block‑DPLR) predictors, then quantizes only the residuals, offering a flexible trade‑off between fidelity and memory usage. In extensive tests on HY‑WorldPlay and MAGI‑1, the reusable configuration outperforms QVG‑4 by up to 4.95 dB PSNR while reducing cache memory by 37–48 %, and the video‑adapted configuration surpasses QVG‑Pro by 3.77 dB PSNR with 33.7 % less memory, all while maintaining comparable latency and reducing temporal discontinuities.
arXiv Computer Vision
Aug 31
DensityKV: Density-Guided KV Cache Compression for Long Video Generation
DensityKV is a training‑free strategy for managing the historical key‑value (KV) cache in autoregressive video diffusion models. It creates a separate token‑level KV bank for each attention head and uses Soft‑Riesz density to measure and limit local redundancy among post‑RoPE keys, thereby preventing the KV archive from growing indefinitely. Experiments on three video generation backbones demonstrate that, with the same KV capacity limit, DensityKV improves long‑horizon consistency and generation stability while keeping persistent storage bounded regardless of rollout length.
arXiv Machine Learning
Oct 5
SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention
arXiv:2610.02953v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compres...
arXiv AI
6d ago
GAAC: Lossless KV Compression for Bandwidth-Efficient LLM Inference on Personal Devices
The paper introduces GAAC, a lossless key‑value (KV) compression method for large language model inference on personal devices. GAAC encodes BF16 exponents with per‑channel base‑plus‑offset codes, adapts code widths across small groups, and reconstructs KV tiles on the fly to avoid full‑cache decompression. Experiments show 1.4× compression for BF16 KV, speedups of up to 1.27× in decode attention, and a 26% reduction in resident KV memory while boosting throughput on NVIDIA and Apple hardware.
arXiv AI
Oct 7
AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free r...
arXiv Computer Vision
Sep 23
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation
arXiv:2609.26425v1 Announce Type: new Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficien...