no code implementations • 16 Mar 2024 • Jun Liu, Chao Wu, Changdi Yang, Hao Tang, Haoye Dong, Zhenglun Kong, Geng Yuan, Wei Niu, Dong Huang, Yanzhi Wang
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices.
1 code implementation • 16 Feb 2024 • Xuan Shen, Zhenglun Kong, Changdi Yang, Zhaoyang Han, Lei Lu, Peiyan Dong, Cheng Lyu, Chih-hsiang Li, Xuehang Guo, Zhihao Shu, Wei Niu, Miriam Leeser, Pu Zhao, Yanzhi Wang
In this paper, we propose EdgeQAT, the Entropy and Distribution Guided QAT for the optimization of lightweight LLMs to achieve inference acceleration on Edge devices.
no code implementations • 9 Dec 2023 • Xuan Shen, Peiyan Dong, Lei Lu, Zhenglun Kong, Zhengang Li, Ming Lin, Chao Wu, Yanzhi Wang
Recent works show that 8-bit or lower weight quantization is feasible with minimal impact on end-to-end task performance, while the activation is still not quantized.
no code implementations • 17 Aug 2023 • Lu Yang, Zhenglun Kong, Ting Li, Xinyi Bai, Zhiye Lin, Hong Cheng
Traditional image stitching focuses on a single panorama frame without considering the spatial-temporal consistency in videos.
1 code implementation • CVPR 2023 • Shengkun Tang, Yaqing Wang, Zhenglun Kong, Tianchi Zhang, Yao Li, Caiwen Ding, Yanzhi Wang, Yi Liang, Dongkuan Xu
To handle this challenge, we propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously in term of input layer-wise similarities with multiple times of early exiting, namely \textbf{MuE}.
1 code implementation • 19 Nov 2022 • Zhenglun Kong, Haoyu Ma, Geng Yuan, Mengshu Sun, Yanyue Xie, Peiyan Dong, Xin Meng, Xuan Shen, Hao Tang, Minghai Qin, Tianlong Chen, Xiaolong Ma, Xiaohui Xie, Zhangyang Wang, Yanzhi Wang
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization.
no code implementations • 15 Nov 2022 • Peiyan Dong, Mengshu Sun, Alec Lu, Yanyue Xie, Kenneth Liu, Zhenglun Kong, Xin Meng, Zhengang Li, Xue Lin, Zhenman Fang, Yanzhi Wang
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices.
1 code implementation • 2 Nov 2022 • Xuan Shen, Zhenglun Kong, Minghai Qin, Peiyan Dong, Geng Yuan, Xin Meng, Hao Tang, Xiaolong Ma, Yanzhi Wang
That is, there exists a subset of input image patches such that a ViT can be trained from scratch by using only this subset of patches and achieve similar accuracy to the ViTs trained by using all image patches.
1 code implementation • 22 Sep 2022 • Geng Yuan, Yanyu Li, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, Jian Ren
Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs.
1 code implementation • 27 Dec 2021 • Zhenglun Kong, Peiyan Dong, Xiaolong Ma, Xin Meng, Mengshu Sun, Wei Niu, Xuan Shen, Geng Yuan, Bin Ren, Minghai Qin, Hao Tang, Yanzhi Wang
Moreover, our framework can guarantee the identified model to meet resource specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile platforms.
Ranked #4 on Efficient ViTs on ImageNet-1K (with DeiT-S)
1 code implementation • NeurIPS 2021 • Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, Siyue Wang, Minghai Qin, Bin Ren, Yanzhi Wang, Sijia Liu, Xue Lin
Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works.
no code implementations • 19 Oct 2021 • Panjie Qi, Edwin Hsing-Mean Sha, Qingfeng Zhuge, Hongwu Peng, Shaoyi Huang, Zhenglun Kong, Yuhong Song, Bingbing Li
Our HP can achieve higher sparsity ratio and is more flexible than other sparsity pattern.
no code implementations • 29 Sep 2021 • Zhenglun Kong, Peiyan Dong, Xiaolong Ma, Xin Meng, Mengshu Sun, Wei Niu, Bin Ren, Minghai Qin, Hao Tang, Yanzhi Wang
Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult.
no code implementations • 16 Jun 2021 • Geng Yuan, Zhiheng Liao, Xiaolong Ma, Yuxuan Cai, Zhenglun Kong, Xuan Shen, Jingyan Fu, Zhengang Li, Chengming Zhang, Hongwu Peng, Ning Liu, Ao Ren, Jinhui Wang, Yanzhi Wang
More importantly, our method does not require extra hardware cost compared to the traditional two-column mapping scheme.
no code implementations • 30 May 2021 • Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang
In this paper, we propose a compression-compilation co-design framework that can guarantee the identified model to meet both resource and real-time specifications of mobile devices.
no code implementations • CVPR 2021 • Zhengang Li, Geng Yuan, Wei Niu, Pu Zhao, Yanyu Li, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu, Kaiyuan Yang, Bin Ren, Yanzhi Wang, Xue Lin
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Bingbing Li, Zhenglun Kong, Tianyun Zhang, Ji Li, Zhengang Li, Hang Liu, Caiwen Ding
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks.
no code implementations • 15 Sep 2020 • Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang
Our framework can guarantee the identified model to meet both resource and real-time specifications of mobile devices, thus achieving real-time execution of large transformer-based models like BERT variants.
no code implementations • 23 Jan 2020 • Zhengang Li, Yifan Gong, Xiaolong Ma, Sijia Liu, Mengshu Sun, Zheng Zhan, Zhenglun Kong, Geng Yuan, Yanzhi Wang
Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations.