DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918438399639552 |
|---|---|
| author | Wen, Jinqi Xie, Tong Wang, Runsheng Li, Meng |
| author_facet | Wen, Jinqi Xie, Tong Wang, Runsheng Li, Meng |
| contents | Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to exploit the potential of the underlying accelerators. However, existing approaches often lead to either limited efficiency gains or degraded output quality because they overlook the inherent fault tolerance of the diffusion model. Therefore, in this paper, we propose DRIFT, a novel algorithmarchitecture co-optimization framework that harnesses the fault tolerance for efficient and reliable diffusion model inference. We first perform a comprehensive resilience analysis on representative diffusion models. Building on these observations, we introduce a fine-grained, resilience-aware DVFS strategy that selectively protects error-sensitive network blocks and timesteps, and a rollback algorithm-based fault tolerance (ABFT) mechanism that adaptively corrects only critical errors by reverting to previous timesteps. We further optimize offloading intervals and reorganize data layouts to reduce memory overhead. Experiments across diverse models and datasets show that DRIFT can achieve on average 36% energy savings through voltage underscaling or 1.7x speedup via overclocking while maintaining generation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09073 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference Wen, Jinqi Xie, Tong Wang, Runsheng Li, Meng Hardware Architecture Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to exploit the potential of the underlying accelerators. However, existing approaches often lead to either limited efficiency gains or degraded output quality because they overlook the inherent fault tolerance of the diffusion model. Therefore, in this paper, we propose DRIFT, a novel algorithmarchitecture co-optimization framework that harnesses the fault tolerance for efficient and reliable diffusion model inference. We first perform a comprehensive resilience analysis on representative diffusion models. Building on these observations, we introduce a fine-grained, resilience-aware DVFS strategy that selectively protects error-sensitive network blocks and timesteps, and a rollback algorithm-based fault tolerance (ABFT) mechanism that adaptively corrects only critical errors by reverting to previous timesteps. We further optimize offloading intervals and reorganize data layouts to reduce memory overhead. Experiments across diverse models and datasets show that DRIFT can achieve on average 36% energy savings through voltage underscaling or 1.7x speedup via overclocking while maintaining generation quality. |
| title | DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2604.09073 |