Alert button
Picture for Jae W. Lee

Jae W. Lee

Alert button

Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

Add code
Bookmark button
Alert button
Feb 16, 2024
Yeonhong Park, Jake Hyun, SangLyul Cho, Bonggeun Sim, Jae W. Lee

Viaarxiv icon

Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching

Add code
Bookmark button
Alert button
Aug 19, 2022
Yeonhong Park, Sunhong Min, Jae W. Lee

Figure 1 for Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
Figure 2 for Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
Figure 3 for Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
Figure 4 for Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
Viaarxiv icon

L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training

Add code
Bookmark button
Alert button
Aug 18, 2022
Jonghyun Bae, Woohyeon Baek, Tae Jun Ham, Jae W. Lee

Figure 1 for L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
Figure 2 for L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
Figure 3 for L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
Figure 4 for L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
Viaarxiv icon

A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation

Add code
Bookmark button
Alert button
Feb 22, 2020
Tae Jun Ham, Sung Jun Jung, Seonghak Kim, Young H. Oh, Yeonhong Park, Yoonho Song, Jung-Hun Park, Sanghee Lee, Kyoung Park, Jae W. Lee, Deog-Kyoon Jeong

Figure 1 for A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation
Figure 2 for A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation
Figure 3 for A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation
Figure 4 for A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation
Viaarxiv icon