VAR-Q Offers Tuning-free KV Cache Quantization for Visual Autoregressive Generation
A new paper introduces VAR-Q, a tuning-free method for quantizing the KV cache in visual autoregressive generation, covering next-scale prediction for images and video and next-frame prediction for video.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-05 05:00 · arXiv cs.CV
VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation