Related papers: Scaling Multi-Node Mixture-of-Experts Inference Us…
The Mixture-of-Experts (MoE) architecture has been widely adopted in large language models (LLMs) to reduce computation cost through model sparsity. Employing speculative decoding (SD) can further accelerate MoE inference by drafting…
The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges:…
Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success in increasing the model capacity of large-scale language models. However, MoE requires incorporating significantly more parameters than the base model…
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…
Recent studies integrate Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) to further enhance the performance of parameter-efficient fine-tuning (PEFT) methods in Large Language Model (LLM) applications. Existing methods employ…
Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…
Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction…
In the past year, large (>100B parameter) mixture-of-expert (MoE) models have become increasingly common in the open domain. While their advantages are often framed in terms of efficiency, prior work has also explored functional…
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…
Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory…
Mixture of Experts (MoE) architectures have emerged as pivotal for scaling Large Language Models (LLMs) efficiently. Fine-grained MoE approaches - utilizing more numerous, smaller experts - have demonstrated potential in improving model…
Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs) often replace whole attention/FFN layers with switch experts or append parallel expert branches,…
Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification, and clustering. For regression and cluster analyses of continuous data, MoE usually use normal experts following the Gaussian…
Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert…
Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them…
The sparse Mixture-of-Experts (MoE) architecture of large language models (LLMs) confronts an inherent issue of load imbalance arising from the simplistic linear router strategy, which ultimately causes the instability and inefficient…
Mixture-of-Experts (MoE) layers activate a subset of model weights, dubbed experts, to improve model performance. MoE is particularly promising for deployment on process-in-memory (PIM) architectures, because PIM can naturally fit experts…
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…
The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to split the pre-training data into semantically relevant groups…
End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer…