Phantom: Temporal Caching for Diffusion Models

Diffusion models have become the dominant paradigm for high-quality image generation, but their iterative inference across tens of timesteps incurs substantial computational overhead. Prior accelerators exploit temporal similarity in diffusion models via differential quantization or output sparsity, yet suffer from increased memory footprint, design complexity, and image degradation. In this work, we present Phantom, an algorithm-architecture co-designed accelerator built on temporal caching. W…

Source: arXiv cs.AR (Hardware Architecture), published 2026-11-05. The summary is the Hub's own; the full story is at the source. Report a rights or accuracy concern