69 citations · 134 across the 7 of their papers we have counts for
8 papers
Taming Speculative Search for Test-Time Scaling in LLM Serving
Jinwoo Jeong, Woohyung Choi, Myeongjae Jeon +1
Test-time scaling has recently emerged as a powerful approach for improving LLM reasoning by allocating additional computation during inference, substantially enhancing accuracy on…
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Xinyue Ma, Suyeon Jeong, Minjia Zhang +3
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hi…
Jarvis: Large-scale Server Monitoring with Adaptive Near-data Processing
Atul Sandur, ChanHo Park, Stavros Volos +2
Rapid detection and mitigation of issues that impact performance and reliability is paramount for large-scale online services. For real-time detection of such issues, datacenter op…
Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
Soobee Lee, Minindu Weerakoon, Jonghyun Choi +3
Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks.…
Approximate Quantiles for Datacenter Telemetry Monitoring
Gangmuk Lim, Mohamed Hassan, Ze Jin +2
Datacenter systems require efficient troubleshooting and effective resource scheduling so as to minimize downtimes and to efficiently utilize limited resources. In doing so, datace…
StreamBox-HBM: Stream Analytics on High Bandwidth Hybrid Memory
Hongyu Miao, Myeongjae Jeon, Gennady Pekhimenko +2
Stream analytics have an insatiable demand for memory and performance. Emerging hybrid memories combine commodity DDR4 DRAM with 3D-stacked High Bandwidth Memory (HBM) DRAM to meet…
Accelerated Training for CNN Distributed Deep Learning through Automatic Resource-Aware Layer Placement
Jay H. Park, Sunghwan Kim, Jinwon Lee +2
The Convolutional Neural Network (CNN) model, often used for image classification, requires significant training time to obtain high accuracy. To this end, distributed training is…
Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads
Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee +3
With widespread advances in machine learning, a number of large enterprises are beginning to incorporate machine learning models across a number of products. These models are typic…