Feb 23, 2023 · ABSTRACT. Achieving efficient execution of machine learning models on mo- bile/edge devices has attracted significant attention recently.

Jan 15, 2022 · In this paper, we propose Moses, a simple and efficient design based on the lottery ticket hypothesis, which fully takes advantage of the features transferable ...

Feb 22, 2023 · In this paper, we propose Moses, a simple yet efficient design based on the lottery ticket hypothesis, which fully takes advantage of the hardware-agnostic ...

Feb 23, 2023 · The Auto-tuning process in a DNN compiler aims to generate a large search space of tensor program configurations and to find the optimal one ...

Moses: Exploiting Cross-device Transferable Features for On-device Tensor Program Optimization. Moses is implemented based on TVM and TenSet. To Cite ...

Moses is proposed, a simple and efficient design based on the lottery ticket hypothesis, which fully takes advantage of the features transferable to the ...

Jan 15, 2022 · In this paper, we propose Moses, a simple and efficient design based on the lottery ticket hypothesis, which fully takes advantage of the features transferable ...

合著作者 ; Moses: Exploiting Cross-Device Transferable Features for on-Device Tensor Program Optimization. Z Zhao, X Shuai, N Ling, N Guan, Z Yan, G Xing.

Moses: Exploiting Cross-device Transferable Features for On-device Tensor Program Optimization by Zhao, Zhihe, et al., HotMobile 2023; TASO: The Tensor ...

Moses: Exploiting Cross-device Transferable Features for On-device Tensor Program Optimization. Accepted by the 24th International Workshop on Mobile ...