CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
- URL: http://arxiv.org/abs/2502.04416v1
- Date: Thu, 06 Feb 2025 14:05:30 GMT
- Title: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
- Authors: Zehua Pei, Lancheng Zou, Hui-Ling Zhen, Xianzhi Yu, Wulong Liu, Sinno Jialin Pan, Mingxuan Yuan, Bei Yu,
- Abstract summary: Large language models (LLMs) achieve impressive performance by scaling model parameters, but this comes with significant inference overhead.
We propose CMoE, a novel framework to efficiently carve MoE models from dense models.
CMoE achieves remarkable performance through efficient expert grouping and lightweight adaptation.
- Score: 33.871080938643566
- License:
- Abstract: Large language models (LLMs) achieve impressive performance by scaling model parameters, but this comes with significant inference overhead. Feed-forward networks (FFNs), which dominate LLM parameters, exhibit high activation sparsity in hidden neurons. To exploit this, researchers have proposed using a mixture-of-experts (MoE) architecture, where only a subset of parameters is activated. However, existing approaches often require extensive training data and resources, limiting their practicality. We propose CMoE (Carved MoE), a novel framework to efficiently carve MoE models from dense models. CMoE achieves remarkable performance through efficient expert grouping and lightweight adaptation. First, neurons are grouped into shared and routed experts based on activation rates. Next, we construct a routing mechanism without training from scratch, incorporating a differentiable routing process and load balancing. Using modest data, CMoE produces a well-designed, usable MoE from a 7B dense model within five minutes. With lightweight fine-tuning, it achieves high-performance recovery in under an hour. We make our code publicly available at https://github.com/JarvisPei/CMoE.
Related papers
- Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models.
Our approach employs activation sparsity to extract experts.
Read-ME outperforms other popular open-source dense models of similar scales.
arXiv Detail & Related papers (2024-10-24T19:48:51Z) - Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities.
In-Context Learning (ICL) and.
Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting.
LLMs to downstream tasks.
We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z) - Search for Efficient Large Language Models [52.98684997131108]
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research.
Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration.
Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
arXiv Detail & Related papers (2024-09-25T21:32:12Z) - BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts [41.83123857437985]
Training MoEs from scratch in a large-scale regime is prohibitively expensive.
We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming.
Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance.
arXiv Detail & Related papers (2024-08-15T17:19:12Z) - Layerwise Recurrent Router for Mixture-of-Experts [42.36093735411238]
Mixture-of-Experts (MoE) architecture stands out for its ability to scale model size without significantly increasing training costs.
Current MoE models often display parameter inefficiency.
We introduce the Layerwise Recurrent Router for Mixture-of-Experts (RMoE)
arXiv Detail & Related papers (2024-08-13T10:25:13Z) - Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes.
This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
arXiv Detail & Related papers (2024-02-22T18:56:07Z) - MoE-LLaVA: Mixture of Experts for Large Vision-Language Models [49.32669226551026]
We propose a simple yet effective training strategy MoE-Tuning for LVLMs.
MoE-LLaVA, a MoE-based sparse LVLM architecture, uniquely activates only the top-k experts through routers.
Experiments show the significant performance of MoE-LLaVA in a variety of visual understanding and object hallucination benchmarks.
arXiv Detail & Related papers (2024-01-29T08:13:40Z) - MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided
Adaptation [68.30497162547768]
We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed.
We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
arXiv Detail & Related papers (2022-04-15T23:19:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.