3 papers
cs.DC2025
Nonuniform-Tensor-Parallelism: Mitigating GPU failure impact for Scaled-up LLM Training
Daiyaan Arfeen, Dheevatsa Mudigere, Ankit More +3
LLM training is scaled up to 10Ks of GPUs by a mix of data-(DP) and model-parallel (MP) execution. Critical to achieving efficiency is tensor-parallel (TP; a form of MP) execution…
cs.DC2024
GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism
Byungsoo Jeon, Mengdi Wu, Shiyi Cao +11
Deep neural networks (DNNs) continue to grow rapidly in size, making them infeasible to train on a single device. Pipeline parallelism is commonly used in existing DNN systems to s…
cs.DC2024
PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
Daiyaan Arfeen, Zhen Zhang, Xinwei Fu +2
Training Deep Neural Networks (DNNs) with billions of parameters generally involves pipeline-parallel (PP) execution. Unfortunately, PP model training can use GPUs inefficiently, e…