[Paper] Budget-Constrained Step-Level Diffusion Caching

Published: (June 11, 2026 at 11:45 AM EDT)
2 min read
Source: arXiv

Source: arXiv - 2606.13496v1

Overview

Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising steps. Existing methods make per-step cache decisions using threshold-based heuristics, without directly optimizing for final output quality. As a result, their inference latency varies across inputs and is difficult to control at deployment. In this work, we propose BudCache, which inverts this formulation: rather than letting per-step error thresholds dictate the runtime cost, we fix the compute budget in advance and search for the cache policy that best preserves the final output. To tackle the combinatorial complexity of step selection, we combine Simulated Annealing with deterministic Hill Climbing. This offline search identifies high-quality cache policies within minutes and introduces no online search or thresholding overhead during inference. When the compute budget is very tight, we further introduce cache-aware schedule alignment, which adapts the time discretization to the selected cache policy to reduce cache-induced trajectory mismatch. Experiments on FLUX.1-dev and Wan2.1 show that BudCache achieves better generation quality than heuristic caching baselines under the same inference budgets. Code is available at https://github.com/Westlake-AGI-Lab/BudCache

Key Contributions

This paper presents research in the following areas:

  • cs.CV

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CV.

Authors

  • Mingkun Lei
  • Tong Zhao
  • Liangyu Yuan
  • Chi Zhang

Paper Information

  • arXiv ID: 2606.13496v1
  • Categories: cs.CV
  • Published: June 11, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »