5 papers
BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion
Bo-Kyeong Kim, Hyoung-Kyu Song, Thibault Castells +1
Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high computing demands due to billion-scale parameters. To enhance efficiency, recent studies have reduc…
Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods
Bo-Kyeong Kim, Geonmin Kim, Tae-Ho Kim +4
Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight mat…
LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
Thibault Castells, Hyoung-Kyu Song, Bo-Kyeong Kim +1
Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDM…
EdgeFusion: On-Device Text-to-Image Generation
Thibault Castells, Hyoung-Kyu Song, Tairen Piao +6
The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent…
SNP: Structured Neuron-level Pruning to Preserve Attention Scores
Kyunghwan Shim, Jaewoong Yun, Shinkook Choi
Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost…