Related papers: No Cache Left Idle: Accelerating diffusion model v…

3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high-fidelity reconstruction. However, their multi-step…

Model autoscaling is the key mechanism to achieve serverless model-as-a-service, but it faces a fundamental trade-off between scaling speed and storage/memory usage to cache parameters, and cannot meet frequent scaling requirements across…

Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that…

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis…

Caching popular contents at the edge of the network can positively impact the performance and future sustainability of wireless networks in several ways, e.g., end-to-end access delay reduction and peak rate increase. In this paper, we aim…

Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the lengthy sampling time of the denoising process remains a significant bottleneck in…

Heterogeneous parallel systems are widely spread nowadays. Despite their availability, their usage and adoption are still limited, and even more rarely they are used to full power. Indeed, compelling new technologies are constantly…

In this paper, we propose a practical and effective approach allowing designers to optimize multi-level cache size at the early system design phase. Our key contribution is to generalize the reuse distance analysis method and develop an…

To mitigate the burden of data labeling, we aim at improving data efficiency for both classification and regression setups in deep learning. However, the current focus is on classification problems while rare attention has been paid to deep…

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-exiting has recently been proposed, where the depth of the…

Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system…

The last decades have seen a surge of interests in distributed computing thanks to advances in clustered computing and big data technology. Existing distributed algorithms typically assume {\it all the data are already in one place}, and…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased…

Diffusion transformer (DiT) achieves remarkable performance in visual generation, but its iterative denoising process combined with larger capacity leads to a high inference cost. Recent works have demonstrated that the iterative denoising…