Int8 ViT on TVM, 1.5 speed up compared with TensorRT

Ruihao Gong
Apr 19, 2021 1 min read Deep learning compiler, Quantization, Transformer

For details, please refer to Link.

Transformer Quantization
Ruihao Gong
Ruihao Gong

My research interests include deep learning fundamental, efficient AI, and their relevant applications such as autonomous driving and AIoT.