Skip to content
arXiv Game World Models & Generation· Bingnan Liu·· 27 d agoPickAI score45

WorldPager: zero-stall tiered memory for long-horizon world models on a single consumer GPU

WorldPager: Zero-Stall Tiered Memory for Long-Horizon World Models on a Single Consumer GPU

AI summary

WorldPager stores the int4 KV memory of interactive world models across GPU, DRAM and NVMe tiers and prefetches it based on camera pose. On a single RTX 4090, it continuously generates 37.5 minutes of video without stalls, with host memory staying constant and a speed of about 9.5 frames per second. On a closed test set, int4 storage showed no measurable quality loss. On long-interval revisits, image quality dropped by about 1 MUSIQ point.

Why it matters

The paper places a world model's KV memory across GPU, DRAM and NVMe tiers with pose-based prefetching, which is useful for readers following long-horizon interactive video generation.

Source: arXiv Game World Models & Generation · arxiv.org