Minsub Kim

DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation

Seongmin Hong, Seungjae Moon, Junsoo Kim et al. · 2022 · 82 citations

Llm Fine-tuning, Gpt-2 Model Inference, Machine Learning +23

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Gunho Park, Baeseong Park, Minsub Kim et al. · arXiv (Cornell University) · 2022 · 20 citations · Full text

Structured Prediction, Llm Fine-tuning, Engineering +21

Reducing tail latency of DNN-based recommender systems using in-storage processing

Minsub Kim, Sungjin Lee · 2020 · 16 citations

Storage Performance, Engineering, Machine Learning +20

DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation

Seongmin Hong, Seungjae Moon, Junsoo Kim et al. · 2022 · 12 citations

What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers

Boseop Kim, HyoungSeok Kim, Sang‐Woo Lee et al. · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021 · 11 citations · Full text

Engineering, Multilingualism, Part-of-speech Tagging +24