MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization Paper • 2405.17873 • Published May 28 • 2
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression Paper • 2406.14909 • Published Jun 21 • 13
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation Paper • 2406.02540 • Published Jun 4 • 2
DiTFastAttn: Attention Compression for Diffusion Transformer Models Paper • 2406.08552 • Published Jun 12 • 22
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding Paper • 2307.15337 • Published Jul 28, 2023 • 36