{"ID":2832213,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06353","arxiv_id":"2512.06353","title":"TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search","abstract":"Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), designed to push the limits of quantization, has demonstrated remarkable success in advancing U-Net quantization to sub-4bit settings while significantly reducing computational and memory overhead. Nevertheless, its application to DiT architectures remains limited and underexplored. In this work, we propose TreeQ, a unified framework addressing key challenges in DiT quantization. First, to tackle inefficient search and proxy misalignment, we introduce Tree Structured Search (TSS). This DiT-specific approach leverages the architecture's linear properties to traverse the solution space in O(n) time while improving objective accuracy through comparison-based pruning. Second, to unify optimization objectives, we propose Environmental Noise Guidance (ENG), which aligns Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) configurations using a single hyperparameter. Third, to mitigate information bottlenecks in ultra-low-bit regimes, we design the General Monarch Branch (GMB). This structured sparse branch prevents irreversible information loss, enabling finer detail generation. Through extensive experiments, our TreeQ framework demonstrates state-of-the-art performance on DiT-XL/2 under W3A3 and W4A4 PTQ/PEFT settings. Notably, our work is the first to achieve near-lossless 4-bit PTQ performance on DiT models. The code and models will be available at https://github.com/racoonykc/TreeQ","short_abstract":"Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), d...","url_abs":"https://arxiv.org/abs/2512.06353","url_pdf":"https://arxiv.org/pdf/2512.06353v1","authors":"[\"Kaicheng Yang\",\"Kaisen Yang\",\"Baiting Wu\",\"Xun Zhang\",\"Qianrui Yang\",\"Haotong Qin\",\"He Zhang\",\"Yulun Zhang\"]","published":"2025-12-06T08:59:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false,"code_links":[{"ID":606207,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2832213,"paper_url":"https://arxiv.org/abs/2512.06353","paper_title":"TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search","repo_url":"https://github.com/racoonykc/TreeQ","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}