Related papers: MoE-Pruner: Pruning Mixture-of-Experts Large Langu…

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue that the separation between the router's decision-making and…

Recent advancements have shown that the Mixture of Experts (MoE) approach significantly enhances the capacity of large language models (LLMs) and improves performance on downstream tasks. Building on these promising results, multi-modal…

Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token compute, but the deployment still requires storing all experts, making expert pruning important for reducing memory and serving overhead.…

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and…

Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. While Mixture-of-Experts (MoE) can make these models more…

Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or…

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prior post-training optimizations, such as inter- and…

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Structured pruning is one of the representative techniques for compressing large language models (LLMs) to reduce GPU memory consumption and accelerate inference speed. It offers significant practical value in improving the efficiency of…

Large Language Models excel at natural language processing tasks, but their massive size leads to high computational and storage demands. Recent works have sought to reduce their model size through layer-wise structured pruning. However,…

Sparse Mixture-of-Experts (MoE) has become a key architecture for scaling large language models (LLMs) efficiently. Recent fine-grained MoE designs introduce hundreds of experts per layer, with multiple experts activated per token, enabling…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies fail to leverage. This motivates us to investigate whether adaptation…

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely hinders their practical deployment. Singular Value…

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion…

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Scaling large language models (LLMs) significantly improves performance but comes with prohibitive computational costs. Mixture-of-Experts (MoE) models offer an efficient alternative, increasing capacity without a proportional rise in…

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…