Vision Transformers (ViTs) achieve strong performance on image recognition and mobile vision applications, but their high-dimensional linear projections and attention computations still impose substantial storage and inference costs. Extremely low-bit quantization is a promising solution, yet ViTs often suffer severe a...
Meng-Yuan Fan, Bo-Kai Huang, Jia-Ming Pan et al.· 0 citations
G$^2$PTQ is presented, a unified PTQ framework with Generalized Gradient Compensation that integrates both first- and second-order information under a globally supervised, block-wise optimization objective and enables better alignment with the full-precision model, outperforming state-of-the-art baselines.
Rui-Kang Liu, Hao-Li Bai, Yuxuan Sun et al.· 0 citations
Real-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied...
Qian Zhang, Yao-Ming Li, Zheng Tan et al.· 0 citations
ReQuant is introduced, a backpropagation-free fixed-grid refinement procedure that takes an existing quantized model as a feasible starting point and iteratively revisits its discrete weight assignments on the fixed quantization grid, and turns the initially fixed PTQ output into an iteratively optimizable discrete sol...
Yongge Ma, Guoan Wang, Feiyu Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
