Dynabits: Token Aware Weight-Activation Quantization for Large Vision-Language Models
Dynabits: Token Aware Weight-Activation Quantization for Large Vision-Language Models
Shigeng Wang,Zhonghong Ou,Hongxing Zhang
2026 · DOI: 10.1109/icassp55912.2026.11461750
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations