24 citations · 36 across the 7 of their papers we have counts for
9 papers
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Songlin Jiang, Zhiyu Li, Terry Kong +5
Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout clusters before the next batch. Transferring a full 1T checkpo…
NCCL M2N: A Layout- and Topology-Aware Collective for Distributed Tensor Resharding
Kaushik Kandadi, Youngeun Kwon, Sreeram Potluri +6
Distributed training and rollout generation often use different tensor layouts, requiring model weights to be resharded across distinct process groups. This M-to-N redistribution i…
LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
Juntaek Lim, Youngeun Kwon, Ranggi Hwang +3
Differential privacy (DP) is widely being employed in the industry as a practical standard for privacy protection. While private training of computer vision or natural language pro…
Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards
Youngeun Kwon, Minsoo Rhu
Personalized recommendation models (RecSys) are one of the most popular machine learning workload serviced by hyperscalers. A critical challenge of training RecSys is its high memo…
Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training
Youngeun Kwon, Yunjae Lee, Minsoo Rhu
Personalized recommendations are one of the most widely deployed machine learning (ML) workload serviced from cloud datacenters. As such, architectural solutions for high-performan…
Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations
Ranggi Hwang, Taehun Kim, Youngeun Kwon +1
Personalized recommendations are the backbone machine learning (ML) algorithm that powers several important application domains (e.g., ads, e-commerce, etc) serviced from cloud dat…
NeuMMU: Architectural Support for Efficient Address Translations in Neural Processing Units
Bongjoon Hyun, Youngeun Kwon, Yujeong Choi +2
To satisfy the compute and memory demands of deep neural networks, neural processing units (NPUs) are widely being utilized for accelerating deep learning algorithms. Similar to ho…
TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning
Youngeun Kwon, Yunjae Lee, Minsoo Rhu
Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper ad…
Beyond the Memory Wall: A Case for Memory-centric HPC System for Deep Learning
Youngeun Kwon, Minsoo Rhu
As the models and the datasets to train deep learning (DL) models scale, system architects are faced with new challenges, one of which is the memory capacity bottleneck, where the…