Search Results for author:
Found 4 papers, 2 papers with code
HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration
Upon detailed analysis, we pinpoint that these discrepancies primarily stem from two aspects: (1) Prior Timestep Disregard, where training ignores the effect of cache usage at earlier timesteps, and (2) Objective Mismatch, where the training target (align predicted noise in each timestep) deviates from the goal of inference (generate the high-quality image).
Temporal Feature Matters: A Framework for Diffusion Model Quantization
However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising.
LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities.
TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
Remarkably, our quantization approach, for the first time, achieves model performance nearly on par with the full-precision model under 4-bit weight quantization.
