Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Lin, Wuwei"'
Autor:
Lai, Ruihang, Shao, Junru, Feng, Siyuan, Lyubomirsky, Steven S., Hou, Bohan, Lin, Wuwei, Ye, Zihao, Jin, Hongyi, Jin, Yuchen, Liu, Jiawei, Jin, Lesheng, Cai, Yaxing, Jiang, Ziheng, Wu, Yong, Park, Sunghyun, Srivastava, Prakalp, Roesch, Jared G., Mowry, Todd C., Chen, Tianqi
Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models. The success of these models has driven demand for deploying them to a diverse set of backend environments. In this pap
Externí odkaz:
http://arxiv.org/abs/2311.02103
Autor:
Feng, Siyuan, Hou, Bohan, Jin, Hongyi, Lin, Wuwei, Shao, Junru, Lai, Ruihang, Ye, Zihao, Zheng, Lianmin, Yu, Cody Hao, Yu, Yong, Chen, Tianqi
Deploying deep learning models on various devices has become an important topic. The wave of hardware specialization brings a diverse set of acceleration primitives for multi-dimensional tensor computations. These new acceleration primitives, along w
Externí odkaz:
http://arxiv.org/abs/2207.04296
Autor:
Shao, Junru, Zhou, Xiyou, Feng, Siyuan, Hou, Bohan, Lai, Ruihang, Jin, Hongyi, Lin, Wuwei, Masuda, Masahiro, Yu, Cody Hao, Chen, Tianqi
Automatic optimization for tensor programs becomes increasingly important as we deploy deep learning in various environments, and efficient optimization relies on a rich search space and effective search. Most existing efforts adopt a search space wh
Externí odkaz:
http://arxiv.org/abs/2205.13603
Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing dense fra
Externí odkaz:
http://arxiv.org/abs/1802.09723