7 papers
LaSR: Context-Aware Speech Recognition via Latent Reasoning
Heyang Liu, Ziyang Cheng, Jiayi Huang +5
Recent advances in Speech Large Language Models (Speech LLMs) have significantly enhanced spoken language understanding and reasoning. However, their contextual awareness is limite…
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…
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…