3 papers
cs.DC2026
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total pa…
cs.LG2025
MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
Dennis Liu, Zijie Yan, Xin Yao +15
Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageab…
cs.CL2023
Aligning Language Models with Offline Learning from Human Feedback
Jian Hu, Li Tao, June Yang +1
Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leverag…