28 citations · 144 across the 32 of their papers we have counts for
24 papers · 1 filter
ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
Sunghyeon Woo, Jaeeun Kil, Hoseung Kim +9
Multi model inference has recently emerged as a prominent paradigm, particularly in the development of agentic AI systems. However, in such scenarios, each model must maintain its…
PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
Sunghyeon Woo, Hoseung Kim, Sunghwan Shim +9
Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a shared context. This execution pa…
CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
Gunho Park, Jeongin Bae, Byeongwook Kim +5
Weight-only quantization is widely used to mitigate the memory-bound nature of LLM inference. Codebook-based methods extend this trend by achieving strong accuracy in the extremely…
AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
Gunho Park, Jeongin Bae, Beomseok Kwon +3
The deployment of large language models (LLMs) is increasingly constrained by memory and latency bottlenecks, motivating the need for quantization techniques that flexibly balance…
An Inquiry into Datacenter TCO for LLM Inference with FP8
Jiwoo Kim, Joonhyung Lee, Gunho Park +4
As large language models (LLMs) continue to scale, the high power consumption of AI accelerators in datacenters presents significant challenges, substantially increasing the total…
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices
Jung Hyun Lee, Jeonghoon Kim, June Yong Yang +4
With the commercialization of large language models (LLMs), weight-activation quantization has emerged to compress and accelerate LLMs, achieving high throughput while reducing inf…
To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability
Joonhyung Lee, Jeongin Bae, Byeongwook Kim +2
The massive computational costs associated with large language model (LLM) pretraining have spurred great interest in reduced-precision floating-point representations to accelerate…
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
June Yong Yang, Byeongwook Kim, Jeongin Bae +5
Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footpri…
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
Sunghyeon Woo, Baeseong Park, Byeongwook Kim +4
Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs du…
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
Jung Hyun Lee, Jeonghoon Kim, Se Jung Kwon +1
Post-training quantization (PTQ) has been gaining popularity for the deployment of deep neural networks on resource-limited devices since unlike quantization-aware training, neithe…
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
Jeonghoon Kim, Jung Hyun Lee, Sungdong Kim +4
Large language models (LLMs) face the challenges in fine-tuning and deployment due to their high memory demands and computational costs. While parameter-efficient fine-tuning (PEFT…
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models
Se Jung Kwon, Jeonghoon Kim, Jeongin Bae +7
There are growing interests in adapting large-scale language models using parameter-efficient fine-tuning methods. However, accelerating the model itself and achieving better infer…
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
Dongjun Kim, Byeonghu Na, Se Jung Kwon +3
Whereas diverse variations of diffusion models exist, extending the linear diffusion into a nonlinear diffusion process is investigated by very few works. The nonlinearity effect h…
Modulating Regularization Frequency for Efficient Compression-Aware Model Training
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +3
While model compression is increasingly important because of large neural network size, compression-aware training is challenging as it needs sophisticated model modifications and…
Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization
Byeongwook Kim, Dongsoo Lee, Yeonju Ro +4
Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimizati…
Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression
Baeseong Park, Se Jung Kwon, Daehwan Oh +2
Even though fine-grained pruning techniques achieve a high compression ratio, conventional sparsity representations (such as CSR) associated with irregular sparsity degrade paralle…
FleXOR: Trainable Fractional Quantization
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +3
Quantization based on the binary codes is gaining attention because each quantized bit can be directly utilized for computations without dequantization using look-up tables. Previo…
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation
Insoo Chung, Byeongwook Kim, Yoonjung Choi +5
The deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is l…
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs
Yongkweon Jeon, Baeseong Park, Se Jung Kwon +3
The number of parameters in deep neural networks (DNNs) is rapidly increasing to support complicated tasks and to improve model accuracy. Correspondingly, the amount of computation…
Learning Low-Rank Approximation for CNNs
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +1
Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural netw…
Network Pruning for Low-Rank Binary Indexing
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim +2
Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning…
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
Se Jung Kwon, Dongsoo Lee, Byeongwook Kim +3
Model compression techniques, such as pruning and quantization, are becoming increasingly important to reduce the memory footprints and the amount of computations. Despite model si…
DeepTwist: Learning Model Compression via Occasional Weight Distortion
Dongsoo Lee, Parichay Kapoor, Byeongwook Kim
Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, qua…
Retraining-Based Iterative Weight Quantization for Deep Neural Networks
Dongsoo Lee, Byeongwook Kim
Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is e…