1 citations · 1 across the 4 of their papers we have counts for
4 papers
Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
Zhendong Zhang
Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate seq…
Flash Window Attention: speedup the attention computation for Swin Transformer
Zhendong Zhang
To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attenti…
Learning Multi-Layered GBDT Via Back Propagation
Zhendong Zhang
Deep neural networks are able to learn multi-layered representation via back propagation (BP). Although the gradient boosting decision tree (GBDT) is effective for modeling tabular…
Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling
Zhendong Zhang
Convolution utilizes a shift-equivalent prior of images, thus leading to great success in image processing tasks. However, commonly used poolings in convolutional neural networks (…