Seongmin Hong
Co-Founder at HyperAccel
Research Interest
- Neural Networks Accelerator
Publication
Conference Papers
Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization
*Minsu Kim, *Seongmin Hong, RyeoWook Ko, Soongyu Choi, Hunjong Lee, Junsoo Kim, Joo-Young Kim, Jongse Park (*equal contribution)
ACM/IEEE International Symposium on Computer Architecture (ISCA), 2025
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation
Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, and Joo-Young Kim
The 55th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2022
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation
Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, and Joo-Young Kim
Hot Chips: A Symposium on High Performance Chips (HOTCHIPS), 2022
NN compactor: Minimizing memory and logic resources for small neural networks
Seongmin Hong, Inho Lee, and Yongjun Park
Design, Automation & Test in Europe Conference & Exhibition (DATE), 2018
Journal Papers
Enabling Energy Efficient Image Encryption using Approximate Memoization
Seongmin Hong, Jaehyung Im, SM Maxharul Islam, Jaehee You, and Yongjun Park
Journal of Semiconductor Technology and Science (JSTS), 2017