🏢 University of Illinois Chicago
PTQ4DiT: Post-training Quantization for Diffusion Transformers
·2510 words·12 mins·
loading
·
loading
AI Generated
Computer Vision
Image Generation
🏢 University of Illinois Chicago
PTQ4DiT achieves 8-bit and even 4-bit weight precision for Diffusion Transformers, significantly improving efficiency for image generation without sacrificing quality.
Induced Model Matching: Restricted Models Help Train Full-Featured Models
·2402 words·12 mins·
loading
·
loading
Large Language Models
🏢 University of Illinois Chicago
Restricted models often outperform full-featured models when training data is limited. This paper introduces Induced Model Matching (IMM), a novel technique that uses a restricted model as a guide to…