infrastructure
The Cached Step Learns How Far It Can Jump
SoftCache turns a diffusion model’s staleness headroom into adaptive step sizes instead of a binary refresh-or-reuse decision.
Summary
SoftCache turns a diffusion model’s staleness headroom into adaptive step sizes instead of a binary refresh-or-reuse decision.
Caching can accelerate diffusion generation by reusing activations, but most methods treat the cache signal as a hard switch. SoftCache interprets the remaining headroom below a refresh threshold as an estimate of reuse error, then takes longer jumps when the cache is fresh and shorter steps as a refresh approaches. The method requires no training or per-backbone settings. On the authors’ FLUX image tests and HunyuanVideo and Wan2.1 video tests, reported speedups ranged from 3.5 to 6.9 times while leading all compared baselines on four fidelity metrics. Those are model- and benchmark-specific results, not a guarantee for every sampler or workload.
Why it matters
SoftCache turns a diffusion model’s staleness headroom into adaptive step sizes instead of a binary refresh-or-reuse decision.
Limits and context
- Those are model- and benchmark-specific results, not a guarantee for every sampler or workload.
Key claims
SoftCache turns a diffusion model’s staleness headroom into adaptive step sizes instead of a binary refresh-or-reuse decision.
Qualification: Those are model- and benchmark-specific results, not a guarantee for every sampler or workload.
Evidence: source-2026-10-18-003
Sources
- arXiv preprint 2610.22369, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.