Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

• URL: http://arxiv.org/abs/2405.15052v2
• Date: Fri, 28 Jun 2024 19:39:45 GMT
• Title: Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training
• Authors: Xianzhi Du, Tom Gunter, Xiang Kong, Mark Lee, Zirui Wang, Aonan Zhang, Nan Du, Ruoming Pang,
• Abstract summary: 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.
• Score: 45.97480866595295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adopt the following setting: 1) use FLOPs or activated parameters as a measure of model complexity; 2) train all models to the same number of tokens. We argue that this setting favors MoE as FLOPs and activated parameters do not accurately measure the communication overhead in sparse layers, leading to a larger actual training budget for MoE. In this work, we revisit the settings by adopting step time as a more accurate measure of model complexity, and by determining the total compute budget under the Chinchilla compute-optimal settings. To efficiently run MoE on modern accelerators, we adopt a 3D sharding method that keeps the dense-to-MoE step time increase within a healthy range. We evaluate MoE and dense LLMs on a set of nine 0-shot and two 1-shot English tasks, as well as MMLU 5-shot and GSM8K 8-shot across three model scales at 6.4B, 12.6B, and 29.6B. Experimental results show that even under these settings, MoE consistently outperform dense LLMs on the speed-accuracy trade-off curve with meaningful gaps. Our full model implementation and sharding strategy has been released at~\url{https://github.com/apple/axlearn}

Related papers

• MoDification: Mixture of Depths Made Easy [36.3113087767816]
  mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. MoDification can achieve up to 1.2x speedup in latency and 1.8x reduction in memory.
  arXiv  Detail & Related papers  (2024-10-18T08:22:07Z)
• LaDiMo: Layer-wise Distillation Inspired MoEfier [1.6199400106794555]
  We propose a novel algorithm, LaDiMo, which efficiently converts a Transformer-based non-MoE model into a MoE model with minimal additional training cost. We demonstrate the effectiveness of our method by converting the LLaMA2-7B model to a MoE model using only 100K tokens.
  arXiv  Detail & Related papers  (2024-08-08T07:37:26Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models [62.4691912312317]
  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.
  arXiv  Detail & Related papers  (2024-04-08T14:39:49Z)
• 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)
• Scaling Sparse Fine-Tuning to Large Language Models [67.59697720719672]
  Large Language Models (LLMs) are difficult to fully fine-tune due to their sheer number of parameters. We propose SpIEL, a novel sparse finetuning method which maintains an array of parameter indices and the deltas of these parameters relative to their pretrained values. We show that SpIEL is superior to popular parameter-efficient fine-tuning methods like LoRA in terms of performance and comparable in terms of run time.
  arXiv  Detail & Related papers  (2024-01-29T18:43:49Z)
• 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)

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.