8 citations · 13 across the 7 of their papers we have counts for
8 papers
GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
Yeonjoon Jung, Daehyun Ahn, Hyungjun Kim +2
Low-Rank Adaptation (LoRA) is a popular method for parameter-efficient fine-tuning (PEFT) of generative models, valued for its simplicity and effectiveness. Despite recent enhancem…
Debunking the CUDA Myth Towards GPU-based AI Systems
Yunjae Lee, Juntaek Lim, Jehyeon Bang +10
This paper presents a comprehensive evaluation of Intel Gaudi NPUs as an alternative to NVIDIA GPUs, which is currently the de facto standard in AI system design. First, we create…
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Dongwon Jo, Taesu Kim, Yulhwa Kim +1
Binarization, which converts weight parameters to binary values, has emerged as an effective strategy to reduce the size of large language models (LLMs). However, typical binarizat…
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
Taesu Kim, Jongho Lee, Daehyun Ahn +4
We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict p…
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
Jiwon Song, Kyungseok Oh, Taesu Kim +3
Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challe…
Squeezing Large-Scale Diffusion Models for Mobile
Jiwoong Choi, Minkyu Kim, Daehyun Ahn +6
The emergence of diffusion models has greatly broadened the scope of high-fidelity image synthesis, resulting in notable advancements in both practical implementation and academic…
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
Changhun Lee, Jungyu Jin, Taesu Kim +2
Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment. To address this challeng…
Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics
Hyungjun Kim, Taesu Kim, Jinseok Kim +1
Artificial Neural Network computation relies on intensive vector-matrix multiplications. Recently, the emerging nonvolatile memory (NVM) crossbar array showed a feasibility of impl…