Related papers: CAMERA: Multi-Matrix Joint Compression for MoE Mod…
The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost. Even in the era of…
Due to the cost-prohibitive nature of training Large Language Models (LLMs), fine-tuning has emerged as an attractive alternative for specializing LLMs for specific tasks using limited compute resources in a cost-effective manner. In this…
Previous work on Universal Transformers (UTs) has demonstrated the importance of parameter sharing across layers. By allowing recurrence in depth, UTs have advantages over standard Transformers in learning compositional generalizations, but…
Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…
Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry and instability…
Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs)…
Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularity, shared experts, load balancing, token dropping - have only been studied one or two at a…
Large Language Models (LLMs) have achieved state-of-the-art accuracies in a variety of natural language processing (NLP) tasks. However, this success comes at the cost of increased model sizes which leads to additional computational burden.…
Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task.…
The Mixture of Experts (MoE) architecture is a cornerstone of modern state-of-the-art (SOTA) large language models (LLMs). MoE models facilitate scalability by enabling sparse parameter activation. However, traditional MoE architecture uses…
The scaling of large language models (LLMs) has revolutionized their capabilities in various tasks, yet this growth must be matched with efficient computational strategies. The Mixture-of-Experts (MoE) architecture stands out for its…
MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…
The recent surge in Large Language Models (LLMs) has garnered significant attention across numerous fields. Fine-tuning is often required to fit general LLMs for a specific domain, like the web-based healthcare system. However, two problems…
In this paper, we aim to build a robust question answering system that can adapt to out-of-domain datasets. A single network may overfit to the superficial correlation in the training distribution, but with a meaningful number of expert…
How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce…
Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under…
The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…
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…
Large Language Models (LLMs) are increasingly deployed as Internet/Web services (LLM-as-a-Service) with strict latency Service-Level Objectives (SLOs) under tight GPU memory budgets. Mixture-of-Experts (MoE) models improve quality and…
Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The…