相关论文: Exploiting Activation Sparsity with Dense to Dynam…

The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy…

Despite the computational efficiency of MoE models, the excessive memory footprint and I/O overhead inherent in multi-expert architectures pose formidable challenges for real-time inference on resource-constrained edge platforms. While…

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make…

Sparse Mixture of Experts (sMoE) has become a pivotal approach for scaling large vision-language models, offering substantial capacity while maintaining computational efficiency through dynamic, sparse activation of experts. However,…

The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data…

Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is…

Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes…

Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational…

Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization. We introduce PreMoE, a training-free framework that…

Sparsely activated Mixture-of-Experts (MoE) models effectively increase the number of parameters while maintaining consistent computational costs per token. However, vanilla MoE models often suffer from limited diversity and specialization…

The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…

Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present \textbf{MoE-X}, a…

Mixture-of-experts networks (MoEs) have demonstrated remarkable efficiency in modern deep learning. Despite their empirical success, the theoretical foundations underlying their ability to model complex tasks remain poorly understood. In…

Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of the model parameters for any given input token. As such,…

Mixture-of-Experts (MoE) architectures enable conditional computation by routing inputs to multiple expert subnetworks and are often motivated as a mechanism for scaling large language models. In this project, we instead study MoE behavior…

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as complex logical…

Sparse mixture of experts (SMoE) is an effective solution for scaling up model capacity without increasing the computational costs. A crucial component of SMoE is the router, responsible for directing the input to relevant experts; however,…

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a…

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse…

Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promising alternative is…