FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs

13 November 2022

Papers citing "FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs"

1 / 1 papers shown

Title
FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference D. Khudia Jianyu Huang Protonu Basu Summer Deng Haixin Liu Jongsoo Park M. Smelyanskiy FedML MQ 49 46 0 13 Jan 2021