Author name cluster

Shenhan Zhu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICLR Conference 2025 Conference Paper

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

Xinyi Liu
Yujie Wang
Fangcheng Fu
Xupeng Miao
Shenhan Zhu
Xiaonan Nie
Bin Cui 0001

Mixture of Experts (MoE) is a widely used technique to expand model sizes for better model quality while maintaining the computation cost constant. In a nutshell, an MoE model consists of multiple experts in each model layer and routes the training tokens to only a fixed number of experts rather than all. In distributed training, as experts are distributed among different GPUs, All-to-All communication is necessary to exchange the training tokens among the GPUs after each time of expert routing. Due to the frequent and voluminous data exchanges, All-to-All communication has become a notable challenge to training efficiency. In this paper, we manage to accelerate All-to-All communication in MoE models from the training sample perspective, which is unexplored so far. In particular, we put forward the observation that tokens in the same training sample have certain levels of locality in expert routing. Motivated by this, we develop NetMoE, which takes such locality into account and dynamically rearranges the placement of training samples to minimize All-to-All communication costs. Specifically, we model the All-to-All communication given the sample placement and formulate an integer programming problem to deduce the optimal placement in polynomial time. Experiments with 32 GPUs show that NetMoE achieves a maximum efficiency improvement of $1.67 \times$ compared with current MoE training frameworks.

Details

NeurIPS Conference 2024 Conference Paper

LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing

Xiaonan Nie
Qibin Liu
Fangcheng Fu
Shenhan Zhu
Xupeng Miao
Xiaoyang Li
Yang Zhang
Shouda Liu

Larger transformer models perform better on various downstream tasks but require more cost to scale up the model size. To efficiently enlarge models, the Mixture-of-Expert (MoE) architecture is widely adopted, which consists of a gate network and a series of experts and keep the training cost constant by routing the input data to a fixed number of experts instead of all. In existing large-scale MoE training systems, experts would be distributed among different GPUs for parallelization, and thus input data requires additional all-to-all communication to access the target expert and conduct corresponding computation. However, upon evaluating the training process of three mainstream MoE models on commonly used GPU clusters, we found that the all-to-all communication ratio averaged around 45\%, which significantly hinders the training efficiency and scalability of MoE models. In this paper, we propose LSH-MoE, a communication-efficient MoE training framework using locality-sensitive hashing (LSH). We first present the problems of scaling MoE training in existing systems and highlight the potential of exploiting token similarity to facilitate data compression. Then, we introduce an efficient LSH-based compression technique, which utilizes the cross-polytope hashing for rapid clustering and implements a residual-based error compensation scheme to alleviate the adverse impact of compression. To verify the effectiveness of our methods, we conduct experiments on both language models (e. g. , RoBERTa, GPT, and T5) and vision models (e. g. , Swin) for both pre-training and fine-tuning tasks. The results demonstrate that our method substantially outperforms its counterparts across different tasks by 1. 28-2. 2$\times$ of speedup.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling

Xupeng Miao
Shenhan Zhu
Fangcheng Fu
Ziyu Guo
Zhi Yang
Yaofeng Tu
Zhihao Jia
Bin Cui

Transformer-based LLMs are becoming increasingly important in various AI applications. However, apart from the success of LLMs, the explosive demand of long context handling capabilities is a key and in-time problem for both academia and industry. Due to the limitations from the quadratic complexity of the attention mechanism, long context scenarios require much more resources for LLM development and deployment, bringing huge challenges to the underlying AI infrastructure. Meanwhile, we observe that there is a trend of reviving previous efficient attention mechanisms to latest LLMs. However, it still remains an open question about how to select from these diverse approaches in practice. In this paper, we answer this question from several aspects. First, we revisit these latest long-context LLM innovations and discuss their relationship with prior approaches with a novel and comprehensive taxonomy. Next, we conduct a thorough evaluation over various types of workloads considering both efficiency and effectiveness. Finally, we provide an in-depth analysis, summarize our key findings, and offer insightful suggestions on the trade-offs of designing and deploying efficient attention mechanisms for Transformer-based LLMs.

PDF Details DOI