Volgen
Changho Hwang
Changho Hwang
Microsoft Research
Geverifieerd e-mailadres voor microsoft.com - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
APUNet: Revitalizing GPU as Packet Processing Accelerator
Y Go, MA Jamshed, YG Moon, C Hwang, KS Park
The 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2017
1272017
Tutel: Adaptive mixture-of-experts at scale
C Hwang, W Cui, Y Xiong, Z Yang, Z Liu, H Hu, Z Wang, R Salas, J Jose, ...
The 6th Conference on Machine Learning and Systems (MLSys), 2023
106*2023
Elastic Resource Sharing for Distributed Deep Learning
C Hwang, T Kim, S Kim, J Shin, KS Park
The 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2021
872021
Confident Multiple Choice Learning
K Lee, C Hwang, KS Park, J Shin
The 34th International Conference on Machine Learning (ICML), 2017
642017
Pre-gated moe: An algorithm-system co-design for fast and scalable mixture-of-expert inference
R Hwang, J Wei, S Cao, C Hwang, X Tang, T Cao, M Yang
2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture …, 2024
272024
Accelerating GNN training with locality-aware partial execution
T Kim, C Hwang, KS Park, Z Lin, P Cheng, Y Miao, L Ma, Y Xiong
The 12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys), 2021
112021
ARK: GPU-driven Code Execution for Distributed Deep Learning
C Hwang, KS Park, R Shu, X Qu, P Cheng, Y Xiong
The 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 0
8*
Pre-gated moe: An algorithm-system co-design for fast and scalable mixture-of-expert inference. In 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)
R Hwang, J Wei, S Cao, C Hwang, X Tang, T Cao, M Yang
IEEE, 2024
62024
Forestcoll: Efficient collective communications on heterogeneous network fabrics
L Zhao, S Maleki, A Shah, Z Yang, H Pourreza, A Krishnamurthy
arXiv preprint arXiv:2402.06787, 2024
32024
A case for two-stage inference with knowledge caching
G Park, C Hwang, KS Park
The 3rd International Workshop on Deep Learning for Mobile Systems and …, 2019
32019
Mixture-of-experts layer with dynamic gating
Y Xiong, C Hwang, W Cui, Y Ziyue, Z Liu, H Hu, Z Wang, RO Salas, J Jose, ...
US Patent App. 18/054,451, 2024
2024
Mixture-of-experts layer with switchable parallel modes
Y Xiong, C Hwang, W Cui, Y Ziyue, Z Liu, H Hu, Z Wang, RO Salas, J Jose, ...
US Patent App. 18/054,446, 2024
2024
Collective communication phases at mixture-of-experts layer
Y Xiong, C Hwang, W Cui, Y Ziyue, Z Liu, H Hu, Z Wang, RO Salas, J Jose, ...
US Patent App. 18/054,452, 2024
2024
Sparse encoding and decoding at mixture-of-experts layer
Y Xiong, C Hwang, W Cui, Y Ziyue, Z Liu, H Hu, Z Wang, RO Salas, J Jose, ...
US Patent App. 18/318,436, 2024
2024
Towards GPU-driven Code Execution for Distributed Deep Learning
C Hwang, KS Park, R Shu, X Qu, P Cheng, Y Xiong
The 3rd Machine Learning for Computer Architecture and Systems, 2022
2022
Immediate Communication for Distributed AI Tasks
J Xin, S Bae, KS Park, M Canini, C Hwang
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–16