Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908948433469440 |
|---|---|
| author | Shen, Tao Zhu, Didi Zhao, Ziyu Li, Zexi Wu, Chao Wu, Fei |
| author_facet | Shen, Tao Zhu, Didi Zhao, Ziyu Li, Zexi Wu, Chao Wu, Fei |
| contents | The remarkable success of foundation models has been driven by scaling laws, demonstrating that model performance improves predictably with increased training data and model size. However, this scaling trajectory faces two critical challenges: the depletion of high-quality public data, and the prohibitive computational power required for larger models, which have been monopolized by tech giants. These two bottlenecks pose significant obstacles to the further development of AI. In this position paper, we argue that leveraging massive distributed edge devices can break through these barriers. We reveal the vast untapped potential of data and computational resources on massive edge devices, and review recent technical advancements in distributed/federated learning that make this new paradigm viable. Our analysis suggests that by collaborating on edge devices, everyone can participate in training large language models with small edge devices. This paradigm shift towards distributed training on edge has the potential to democratize AI development and foster a more inclusive AI community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08223 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices Shen, Tao Zhu, Didi Zhao, Ziyu Li, Zexi Wu, Chao Wu, Fei Distributed, Parallel, and Cluster Computing The remarkable success of foundation models has been driven by scaling laws, demonstrating that model performance improves predictably with increased training data and model size. However, this scaling trajectory faces two critical challenges: the depletion of high-quality public data, and the prohibitive computational power required for larger models, which have been monopolized by tech giants. These two bottlenecks pose significant obstacles to the further development of AI. In this position paper, we argue that leveraging massive distributed edge devices can break through these barriers. We reveal the vast untapped potential of data and computational resources on massive edge devices, and review recent technical advancements in distributed/federated learning that make this new paradigm viable. Our analysis suggests that by collaborating on edge devices, everyone can participate in training large language models with small edge devices. This paradigm shift towards distributed training on edge has the potential to democratize AI development and foster a more inclusive AI community. |
| title | Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2503.08223 |