Boosting QA Performance Through SA-Net and AA-Net with the Read+Verify Framework von Tang, Liang, Qi, Qianqian, Shang, Qinghua, Cai, Yuguang, Liu, Jiamou, Witbrock, Michael, lv, Kaokao

Volltext

TEQ: Trainable Equivalent Transformation for Quantization of LLMs von Cheng, Wenhua, Cai, Yiyang, Lv, Kaokao, Shen, Haihao

Volltext bestellen

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs von Cheng, Wenhua, Zhang, Weiwei, Shen, Haihao, Cai, Yiyang, He, Xin, Lv, Kaokao, Liu, Yi

Volltext bestellen

Effective Quantization for Diffusion Models on CPUs von Chang, Hanwen, Shen, Haihao, Cai, Yiyang, Ye, Xinyu, Xu, Zhenzhong, Cheng, Wenhua, Lv, Kaokao, Zhang, Weiwei, Lu, Yintong, Guo, Heng

Volltext bestellen

TEQ: Trainable Equivalent Transformation for Quantization of LLMs von Cheng, Wenhua, Cai, Yiyang, Lv, Kaokao, Shen, Haihao

Volltext

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs von Cheng, Wenhua, Zhang, Weiwei, Shen, Haihao, Cai, Yiyang, He, Xin, Lv, Kaokao, Liu, Yi

Volltext