Related papers: Lynx: Enabling Efficient MoE Inference through Dyn…

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching…

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…

This paper revisits the implementation of $\textbf{L}$oad-$\textbf{b}$alancing $\textbf{L}$oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is defined as $N_E \sum_{i=1}^{N_E} f_i p_i$, where $N_E$ is the…

Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains unclear how close existing MoE architectures are to optimal…

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two…

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE…

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising results.However, the performance of SMoE heavily depends on the…

Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instruction-conditioning has become the dominant approach for…

Federated instruction tuning of large language models (LLMs) is challenged by significant data heterogeneity across clients, demanding robust personalization. The Mixture of Experts (MoE) architecture, where experts can specialize in…

Mixture-of-Expert (MoE) models enable efficient inference by employing smaller experts and activating only a subset of them per token. MoE serving engines distribute experts across multiple GPUs and route tokens to appropriate GPUs at…

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…

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 garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does not alleviate the massive memory requirements of networks,…

Many studies have revealed that large language models (LLMs) exhibit uneven awareness of different contextual positions. Their limited context awareness can lead to overlooking critical information and subsequent task failures. While…

Efficient inference is a critical challenge in deep generative modeling, particularly as diffusion models grow in capacity and complexity. While increased complexity often improves accuracy, it raises compute costs, latency, and memory…

The advent of Large Language Models (LLMs) has ushered in a new era of artificial intelligence, with the potential to transform various sectors through automation and insightful analysis. The Mixture of Experts (MoE) architecture has been…

Serving large Mixture-of-Experts (MoE) models is challenging because of their large memory footprints, heterogeneous resource demands, and highly dynamic inference workloads. Most existing MoE inference systems deploy the entire model as a…

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…