1 citations · 1 across the 4 of their papers we have counts for
4 papers
Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate
Jaemin Kim, Sungkyun Kim, Junyeol Lee +1
Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without re…
Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
Sungkyun Kim, Jaemin Kim, Dogyung Yoon +3
LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple…
ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference
Hyungjun Oh, Kihong Kim, Jaemin Kim +4
This paper presents ExeGPT, a distributed system designed for constraint-aware LLM inference. ExeGPT finds and runs with an optimal execution schedule to maximize inference through…
Scheduling Optimization Techniques for Neural Network Training
Hyungjun Oh, HyeongJu Kim, Jiwon Seo
Neural network training requires a large amount of computation and thus GPUs are often used for the acceleration. While they improve the performance, GPUs are underutilized during…