Budget-Constrained Step-Level Diffusion Caching
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
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
BAG: Budget-Aware Gating for Diffusion Caching
Diffusion caching is a lightweight strategy that accelerates Diffusion Transformers (DiTs) by reusing intermediate features across denoising steps, but existing paradigms face a fundamental trade-off: online heuristics l…
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerati…
Video GenerationReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE
Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations acr…
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives,…
SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
While Diffusion Language Models (DLMs) offer a flexible, arbitrary-order alternative to the autoregressive paradigm, their non-causal nature precludes standard KV caching, forcing costly hidden state recomputation at eve…