Junsoo Kim

18 papers A* 2B 1Misc 1Journal 10Unranked 4
YearRankTypeTitle / Venue / Authors
2025 B conf
ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput.
ISPASS
Junsoo Kim, Hunjong Lee, Geonwoo Ko, Gyubin Choi, Seri Ham, Seongmin Hong, Joo-Young Kim
2025 J jnl
ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput.
CoRR
Junsoo Kim, Hunjong Lee, Geonwoo Ko, Gyubin Choi, Seri Ham, Seongmin Hong, Joo-Young Kim
2025 A* conf
Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization.
ISCA
Minsu Kim, Seongmin Hong, Ryeowook Ko, Soongyu Choi, Hunjong Lee, Junsoo Kim, Joo-Young Kim, Jongse Park
2025 J jnl
Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization.
CoRR
Minsu Kim, Seongmin Hong, Ryeowook Ko, Soongyu Choi, Hunjong Lee, Junsoo Kim, Joo-Young Kim, Jongse Park
2024 J jnl
A Latency Processing Unit: A Latency-Optimized and Highly Scalable Processor for Large Language Model Inference.
IEEE Micro
Seungjae Moon, Jung-Hoon Kim, Junsoo Kim, Seongmin Hong, Junseo Cha, Minsu Kim, Sukbin Lim, Gyubin Choi, Dongjin Seo, Jongho Kim, Hunjong Lee, Hyunjun Park, Ryeowook Ko, Soongyu Choi, Jongse Park, Jinwon Lee, Joo-Young Kim
2024 J jnl
EPU: An Energy-Efficient Explainable AI Accelerator With Sparsity-Free Computation and Heat Map Compression/Pruning.
IEEE J. Solid State Circuits
Junsoo Kim, Seunghee Han, Geonwoo Ko, Ji-Hoon Kim, Changha Lee, Taewoo Kim, Chan-Hyun Youn, Joo-Young Kim
2024 J jnl
LPU: A Latency-Optimized and Highly Scalable Processor for Large Language Model Inference.
CoRR
Seungjae Moon, Jung-Hoon Kim, Junsoo Kim, Seongmin Hong, Junseo Cha, Minsu Kim, Sukbin Lim, Gyubin Choi, Dongjin Seo, Jongho Kim, Hunjong Lee, Hyunjun Park, Ryeowook Ko, Soongyu Choi, Jongse Park, Jinwon Lee, Joo-Young Kim
2023 — conf
A 26.55TOPS/W Explainable AI Processor with Dynamic Workload Allocation and Heat Map Compression/Pruning.
CICC
Junsoo Kim, Geonwoo Ko, Ji-Hoon Kim, Changha Lee, Taewoo Kim, Chan-Hyun Youn, Joo-Young Kim
2023 — conf
HyperAccel Latency Processing Unit (LPU
HCS
Seungjae Moon, Junsoo Kim, Jung-Hoon Kim, Junseo Cha, Gyubin Choi, Seongmin Hong, Joo-Young Kim
2023 J jnl
T-PIM: An Energy-Efficient Processing-in-Memory Accelerator for End-to-End On-Device Training.
IEEE J. Solid State Circuits
Jaehoon Heo, Junsoo Kim, Sukbin Lim, Wontak Han, Joo-Young Kim
2022 — conf
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
HCS
Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, Joo-Young Kim
2022 A* conf
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
MICRO
Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, Joo-Young Kim
2022 J jnl
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
CoRR
Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, Joo-Young Kim
2022 J jnl
Design of Processing-in-Memory With Triple Computational Path and Sparsity Handling for Energy-Efficient DNN Training.
IEEE J. Emerg. Sel. Topics Circuits Syst.
Wontak Han, Jaehoon Heo, Junsoo Kim, Sukbin Lim, Joo-Young Kim
2022 J jnl
Federated Onboard-Ground Station Computing With Weakly Supervised Cascading Pyramid Attention Network for Satellite Image Analysis.
IEEE Access
Taewoo Kim, Minsu Jeon, Changha Lee, Junsoo Kim, Geonwoo Ko, Joo-Young Kim, Chan-Hyun Youn
2022 Misc conf
OpenMDS: An Open-Source Shell Generation Framework for High-Performance Design on Multi-Die FPGAs.
FCCM
Gyeongcheol Shin, Junsoo Kim, Joo-Young Kim
2022 J jnl
OpenMDS: An Open-Source Shell Generation Framework for High-Performance Design on Xilinx Multi-Die FPGAs.
IEEE Comput. Archit. Lett.
Gyeongcheol Shin, Junsoo Kim, Joo-Young Kim
2022 — conf
T-PIM: A 2.21-to-161.08TOPS/W Processing-In-Memory Accelerator for End-to-End On-Device Training.
CICC
Jaehoon Heo, Junsoo Kim, Wontak Han, Sukbin Lim, Joo-Young Kim