Related papers: SP-MoE: Speculative Decoding and Prefetching for A…

Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing model size proportionally increases the model's computation footprint. In this work, we seek…

Recent efforts on Diffusion Mixture-of-Experts (MoE) models have primarily focused on developing more sophisticated routing mechanisms. However, we observe that the underlying architectural configuration space remains markedly…

The deployment of large-scale Mixture-of-Experts (MoE) models on edge devices presents significant challenges due to memory constraints. While MoE architectures enable efficient utilization of computational resources by activating only a…

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy.…

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

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,…

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms…

Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We…

In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational…

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Mixture-of-Experts (MoE) enhances model performance while maintaining computational efficiency, making it well-suited for large-scale applications. Conventional mixture-of-experts (MoE) architectures suffer from suboptimal coordination…

In deep learning, mixture-of-experts (MoE) activates one or few experts (sub-networks) on a per-sample or per-token basis, resulting in significant computation reduction. The recently proposed \underline{p}atch-level routing in…

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for training LLMs to…

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to…