Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

• URL: http://arxiv.org/abs/2404.05567v1
• Date: Mon, 8 Apr 2024 14:39:49 GMT
• Title: Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models
• Authors: Bowen Pan, Yikang Shen, Haokun Liu, Mayank Mishra, Gaoyuan Zhang, Aude Oliva, Colin Raffel, Rameswar Panda,
• Abstract summary: Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$times$ compared to dense models without sacrificing performance. We propose a hybrid dense training and sparse inference framework for MoE models (DS-MoE) which achieves strong computation and parameter efficiency.
• Score: 62.4691912312317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally require 2-4$\times$ times more parameters to achieve comparable performance to a dense model, which incurs larger GPU memory requirements and makes MoE models less efficient in I/O-bounded scenarios like autoregressive generation. In this work, we propose a hybrid dense training and sparse inference framework for MoE models (DS-MoE) which achieves strong computation and parameter efficiency by employing dense computation across all experts during training and sparse computation during inference. Our experiments on training LLMs demonstrate that our DS-MoE models are more parameter-efficient than standard sparse MoEs and are on par with dense models in terms of total parameter size and performance while being computationally cheaper (activating 30-40% of the model's parameters). Performance tests using vLLM show that our DS-MoE-6B model runs up to $1.86\times$ faster than similar dense models like Mistral-7B, and between $1.50\times$ and $1.71\times$ faster than comparable MoEs, such as DeepSeekMoE-16B and Qwen1.5-MoE-A2.7B.

Related papers

• Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training [45.97480866595295]
  Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. We adopt a 3D sharding method that keeps the dense-to-MoE step time increase within a healthy range.
  arXiv  Detail & Related papers  (2024-05-23T21:00:53Z)
• Toward Inference-optimal Mixture-of-Expert Large Language Models [55.96674056805708]
  We study the scaling law of MoE-based large language models (LLMs) We find that MoEs with a few (4/8) experts are the most serving efficient solution under the same performance, but costs 2.5-3.5x more in training. We propose to amend the scaling law of MoE by introducing inference efficiency as another metric besides the validation loss.
  arXiv  Detail & Related papers  (2024-04-03T16:33:42Z)
• Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes [91.58845026796149]
  We introduce Distilling step-by-step, a new mechanism that trains small models that outperform large language models. We present three findings across 4 NLP benchmarks.
  arXiv  Detail & Related papers  (2023-05-03T17:50:56Z)
• Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production [7.056223012587321]
  We introduce a highly efficient inference framework with several optimization approaches to accelerate the computation of sparse models. We are able to deploy 136x larger models with 27% less cost and significantly better quality compared to the existing solutions.
  arXiv  Detail & Related papers  (2022-11-18T03:43:52Z)
• Efficient Large Scale Language Modeling with Mixtures of Experts [61.45159383372181]
  Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings.
  arXiv  Detail & Related papers  (2021-12-20T17:05:11Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Scalable and Efficient MoE Training for Multitask Multilingual Models [55.987536562357086]
  We develop a system capable of scaling MoE models efficiently to trillions of parameters. We also present new training methods to improve MoE sample efficiency and leverage expert pruning strategy to improve time efficiency. A model trained with 10 billion parameters on 50 languages can achieve state-of-the-art performance in Machine Translation (MT) and multilingual natural language generation tasks.
  arXiv  Detail & Related papers  (2021-09-22T00:57:46Z)

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.