Related papers: EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
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…
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,…
We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only around 5\% of the total parameters are activated per input token. This extreme…
Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…
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…
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…
Standard LoRA fine-tuning of Mixture-of-Experts (MoE) models applies adapters to every expert, yet our profiling shows that per-layer expert routing is highly skewed: a small subset of experts handles most tokens in each layer, while many…
Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise…
Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…
Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…
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…
Modern Mixture-of-Experts (MoE) language models are designed based on total parameters (memory footprint) and active parameters (inference cost). However, we find these two factors alone are insufficient to describe an optimal architecture.…
Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fragile. Methods such as DenseMixer and ESFT mitigate router collapse with dense mixing or…
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.…
The feedforward (FFW) layers in standard transformer architectures incur a linear increase in computational costs and activation memory as the hidden layer width grows. Sparse mixture-of-experts (MoE) architectures have emerged as a viable…
Sparse Mixture-of-Experts (SMoE) models represent a significant advancement in large language model (LLM) development through their efficient parameter utilization. These models achieve substantial performance improvements at reduced…
In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory…
Human education system trains one student by multiple experts. Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts. However, sparse MoE model is easy to overfit, hard to deploy, and not hardware-friendly…
Mixture-of-Experts (MoE) has emerged as a promising sparse paradigm for scaling up pre-trained models (PTMs) with remarkable cost-effectiveness. However, the dynamic nature of MoE leads to rapid fluctuations and imbalances in expert loads…
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…