Parallel Scaling Law for Language Models

• URL: http://arxiv.org/abs/2505.10475v1
• Date: Thu, 15 May 2025 16:24:45 GMT
• Title: Parallel Scaling Law for Language Models
• Authors: Mouxiang Chen, Binyuan Hui, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Jianling Sun, Junyang Lin, Zhongxin Liu,
• Abstract summary: We introduce the third and more inference-efficient scaling paradigm: increasing the model's parallel computation during both training and inference time.<n>We theoretically propose a new scaling law and validate it through large-scale pre-training, which shows that a model with $P$ parallel streams is similar to scaling the parameters by $O(log P)$ while showing superior inference efficiency.
• Score: 45.799251718923614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce the third and more inference-efficient scaling paradigm: increasing the model's parallel computation during both training and inference time. We apply $P$ diverse and learnable transformations to the input, execute forward passes of the model in parallel, and dynamically aggregate the $P$ outputs. This method, namely parallel scaling (ParScale), scales parallel computation by reusing existing parameters and can be applied to any model structure, optimization procedure, data, or task. We theoretically propose a new scaling law and validate it through large-scale pre-training, which shows that a model with $P$ parallel streams is similar to scaling the parameters by $O(\log P)$ while showing superior inference efficiency. For example, ParScale can use up to 22$\times$ less memory increase and 6$\times$ less latency increase compared to parameter scaling that achieves the same performance improvement. It can also recycle an off-the-shelf pre-trained model into a parallelly scaled one by post-training on a small amount of tokens, further reducing the training budget. The new scaling law we discovered potentially facilitates the deployment of more powerful models in low-resource scenarios, and provides an alternative perspective for the role of computation in machine learning.

Related papers

• Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo [22.7130140114906]
  We study the scaling law behavior of DiLoCo when training LLMs under a fixed compute budget.<n>We find that DiLoCo scales both predictably and robustly with model size.<n>When well-tuned, DiLoCo scales better than data-parallel training with model size, and can outperform data-parallel training even at small model sizes.
  arXiv  Detail & Related papers  (2025-03-12T20:04:38Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism [17.006352664497122]
  We develop a practical implementation with PyTorch Fully Shard Data Parallel.<n>We demonstrate that our proposed approaches outperform constant batch sizes.<n>We also theoretical guarantees for such adaptive batch size schedules.
  arXiv  Detail & Related papers  (2024-12-30T17:55:28Z)
• TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters [102.1116808722299]
  We introduce TokenFormer, a scalable architecture for scaling Transformers.<n>By treating model parameters as tokens, we replace all the linear projections in Transformers.<n>Our model scales from 124M to 1.4B parameters by incrementally adding new key-value parameter pairs.
  arXiv  Detail & Related papers  (2024-10-30T16:19:00Z)
• Retentive Network: A Successor to Transformer for Large Language Models [91.6652200825638]
  We propose Retentive Network (RetNet) as a foundation architecture for large language models. We theoretically derive the connection between recurrence and attention. Experimental results on language modeling show that RetNet achieves favorable scaling results, parallel training, low-cost deployment, and efficient inference.
  arXiv  Detail & Related papers  (2023-07-17T16:40:01Z)
• Does compressing activations help model parallel training? [64.59298055364336]
  We present the first empirical study on the effectiveness of compression methods for model parallelism. We implement and evaluate three common classes of compression algorithms. We evaluate these methods across more than 160 settings and 8 popular datasets.
  arXiv  Detail & Related papers  (2023-01-06T18:58:09Z)
• TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models [60.23234205219347]
  TeraPipe is a high-performance token-level pipeline parallel algorithm for synchronous model-parallel training of Transformer-based language models. We show that TeraPipe can speed up the training by 5.0x for the largest GPT-3 model with 175 billion parameters on an AWS cluster.
  arXiv  Detail & Related papers  (2021-02-16T07:34:32Z)

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.