ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs

1 code implementation • 6 Oct 2022 • Yujia Zhai, Chengquan Jiang, Leyuan Wang, Xiaoying Jia, Shang Zhang, Zizhong Chen, Xin Liu, Yibo Zhu

In this paper, we present ByteTransformer, a high-performance transformer boosted for variable-length inputs.

Vocal Bursts Intensity Prediction

Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance

no code implementations • 25 Oct 2021 • Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, Yibo Zhu

Today's auto-tuners (e. g., AutoTVM, Ansor) generate efficient tensor programs by navigating a large search space to identify effective implementations, but they do so with opaque hardware details.