Related papers: Remoe: Towards Efficient and Low-Cost MoE Inferenc…

The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level scaling methods (e.g., Chain-of-Thought). We introduce hyper-parallel scaling, a complementary framework that improves…

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 skewed expert workloads across different modalities. During…

Recent large language models (LLMs) have tended to leverage sparsity to reduce computations, employing the sparsely activated mixture-of-experts (MoE) technique. MoE introduces four modules, including token routing, token communication,…

Mixture-of-Experts (MoE) has emerged as a practical approach to scale up parameters for the Transformer model to achieve better generalization while maintaining a sub-linear increase in computation overhead. Current MoE models are mainly…

Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces…

This paper presents MoE-Infinity, an efficient MoE inference system designed for personal machines with limited GPU memory capacity. The key idea for MoE-Infinity is that on personal machines, which are often single-user environments,…

The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these performance gains into practical edge deployment remains…

With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has…

Mixture-of-Experts (MoE) large language models (LLM) have memory requirements that often exceed the GPU memory capacity, requiring costly parameter movement from secondary memories to the GPU for expert computation. In this work, we present…

The computational sparsity of Mixture-of-Experts (MoE) models enables sub-linear growth in compute cost as model size increases, thus offering a scalable path to training massive neural networks. However, existing implementations suffer…

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prior post-training optimizations, such as inter- and…

Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires all experts to reside in memory, creating a gap between the…

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer…

The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solutions have been proposed to utilize GPU clusters made up of both…

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes,creating a rigidity that fails to…

Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation.…

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computational demands while easily scaling the model size. In MoE…