SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity

Z Fan, S Dai, R Venkatesan, D Sylvester… - arxiv preprint arxiv …, 2025 - arxiv.org
Diffusion models have gained significant popularity in image generation tasks. However,
generating high-quality content remains notably slow because it requires running model …

PrecisionProbe: Non-intrusive Performance Analysis Tool for Deep Learning Recommendation Models

W Peng, J Wang, T Wo, R Yang - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Deep learning recommendation models (DLRM) exploit user behaviors such as clicks,
browse footprints, preferences, etc. for improved personalized experiences. However, in the …