7 papers
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Shwai He, Weilin Cai, Jiayi Huang +1
The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance performance and efficiency. However, u…
ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
Yingping Wang, Yi Wu, Xiangyu Wu +4
Mixture-of-Experts (MoE) architectures are widely used in modern large language models and multimodal models. However, inference efficiency is often limited by highly dynamic and s…
Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
Zhibin Wang, Zhonghui Zhang, Yuhang Zhou +8
Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been pr…
DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction
Weilin Cai, Le Qin, Shwai He +3
Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be vi…
Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts
Weilin Cai, Juyong Jiang, Le Qin +3
Expert parallelism has emerged as a key strategy for distributing the computational workload of sparsely-gated mixture-of-experts (MoE) models across multiple devices, enabling the…
MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training
Weilin Cai, Le Qin, Jiayi Huang
As large language models continue to scale up, distributed training systems have expanded beyond 10k nodes, intensifying the importance of fault tolerance. Checkpoint has emerged a…