Alert button
Picture for Gyeong-In Yu

Gyeong-In Yu

Alert button

Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs

Jan 23, 2022
Taebum Kim, Eunji Jeong, Geon-Woo Kim, Yunmo Koo, Sehoon Kim, Gyeong-In Yu, Byung-Gon Chun

Figure 1 for Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
Figure 2 for Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
Figure 3 for Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
Figure 4 for Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs
Viaarxiv icon

Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

Dec 04, 2020
Woosuk Kwon, Gyeong-In Yu, Eunji Jeong, Byung-Gon Chun

Figure 1 for Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
Figure 2 for Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
Figure 3 for Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
Figure 4 for Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
Viaarxiv icon

A Tensor Compiler for Unified Machine Learning Prediction Serving

Oct 19, 2020
Supun Nakandala, Karla Saur, Gyeong-In Yu, Konstantinos Karanasos, Carlo Curino, Markus Weimer, Matteo Interlandi

Figure 1 for A Tensor Compiler for Unified Machine Learning Prediction Serving
Figure 2 for A Tensor Compiler for Unified Machine Learning Prediction Serving
Figure 3 for A Tensor Compiler for Unified Machine Learning Prediction Serving
Figure 4 for A Tensor Compiler for Unified Machine Learning Prediction Serving
Viaarxiv icon

Accelerating Multi-Model Inference by Merging DNNs of Different Weights

Sep 28, 2020
Joo Seong Jeong, Soojeong Kim, Gyeong-In Yu, Yunseong Lee, Byung-Gon Chun

Figure 1 for Accelerating Multi-Model Inference by Merging DNNs of Different Weights
Figure 2 for Accelerating Multi-Model Inference by Merging DNNs of Different Weights
Figure 3 for Accelerating Multi-Model Inference by Merging DNNs of Different Weights
Figure 4 for Accelerating Multi-Model Inference by Merging DNNs of Different Weights
Viaarxiv icon

Stage-based Hyper-parameter Optimization for Deep Learning

Nov 24, 2019
Ahnjae Shin, Dong-Jin Shin, Sungwoo Cho, Do Yoon Kim, Eunji Jeong, Gyeong-In Yu, Byung-Gon Chun

Figure 1 for Stage-based Hyper-parameter Optimization for Deep Learning
Figure 2 for Stage-based Hyper-parameter Optimization for Deep Learning
Figure 3 for Stage-based Hyper-parameter Optimization for Deep Learning
Figure 4 for Stage-based Hyper-parameter Optimization for Deep Learning
Viaarxiv icon

Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach

Jun 10, 2019
Gyeong-In Yu, Saeed Amizadeh, Artidoro Pagnoni, Byung-Gon Chun, Markus Weimer, Matteo Interlandi

Figure 1 for Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach
Figure 2 for Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach
Figure 3 for Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach
Viaarxiv icon

JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs

Dec 04, 2018
Eunji Jeong, Sungwoo Cho, Gyeong-In Yu, Joo Seong Jeong, DongJin Shin, Byung-Gon Chun

Figure 1 for JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
Figure 2 for JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
Figure 3 for JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
Figure 4 for JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs
Viaarxiv icon

Improving the Expressiveness of Deep Learning Frameworks with Recursion

Sep 04, 2018
Eunji Jeong, Joo Seong Jeong, Soojeong Kim, Gyeong-In Yu, Byung-Gon Chun

Figure 1 for Improving the Expressiveness of Deep Learning Frameworks with Recursion
Figure 2 for Improving the Expressiveness of Deep Learning Frameworks with Recursion
Figure 3 for Improving the Expressiveness of Deep Learning Frameworks with Recursion
Figure 4 for Improving the Expressiveness of Deep Learning Frameworks with Recursion
Viaarxiv icon