Search Results

SysML 19: Zhihao Jia, Optimizing DNN Computation with Relaxed Graph Substitutions

SysML 19: Zhihao Jia, Optimizing DNN Computation with Relaxed Graph Substitutions

SysML 19: Jia Zhihao, Beyond Data and Model Parallelism for Deep Neural Networks

SysML 19: Jia Zhihao, Beyond Data and Model Parallelism for Deep Neural Networks

Opt. DNN Computation with Relaxed Graph Substitutions & TASO

Opt. DNN Computation with Relaxed Graph Substitutions & TASO

TASO: Optimizing Deep Learning Computation with Automated Generation of Graph Substitutions

TASO: Optimizing Deep Learning Computation with Automated Generation of Graph Substitutions

SysML 19: Dan Moldovan, AutoGraph: Imperative-style Coding with Graph-based Performance

SysML 19: Dan Moldovan, AutoGraph: Imperative-style Coding with Graph-based Performance

CMU Prof Zhihao Jia on Automatically Optimizing ML with TASO and PET | Stanford MLSys #43

CMU Prof Zhihao Jia on Automatically Optimizing ML with TASO and PET | Stanford MLSys #43

Computational Graph Optimization: Cuda Kernel Fusion, Initial Report

Computational Graph Optimization: Cuda Kernel Fusion, Initial Report

[FlexFlow Bootcamp 2020] Performance Autotuning and Profiling in FlexFlow

[FlexFlow Bootcamp 2020] Performance Autotuning and Profiling in FlexFlow

OSDI '21 - PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated

OSDI '21 - PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated

2019 TVM and Deep Learning Compilation Conference: Afternoon Session 2

2019 TVM and Deep Learning Compilation Conference: Afternoon Session 2

Compiler Development: Base of Computational Graph

Compiler Development: Base of Computational Graph

Yangqing Jia, VP of Alibaba Group and President of Data Platforms at Alibaba Cloud Intelligence

Yangqing Jia, VP of Alibaba Group and President of Data Platforms at Alibaba Cloud Intelligence