Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization.
Haocheng Xi, Yuxiang Chen, Kang Zhao, Kai Jun Teh, Jianfei Chen, Jun Zhu
Browse the full ICML paper archive.
Haocheng Xi, Yuxiang Chen, Kang Zhao, Kai Jun Teh, Jianfei Chen, Jun Zhu
Browse the full ICML paper archive.