Abstract:Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical analysis. This paper presents the first comprehensive large-scale evaluation of 118 transformer models across seven distinct architectural categories, revealing fundamental performance walls that manifest as hard deployment constraints. Our systematic benchmarking methodology uncovers a critical scalability crisis: while 88.1% of models successfully process sequences up to 512 tokens, this drops dramatically to 44.9% at 1024 tokens, with complete failure (0%) at 2048 tokens. Through rigorous analysis of loading times, memory consumption, and computational efficiency across sequence lengths from 128 to 2048 tokens, we demonstrate that compressed models achieve superior parameter efficiency (649.2 tokens/sec/M parameters) compared to large generative models (12.5 tokens/sec/M). Our findings challenge prevailing scaling assumptions and provide the first quantitative evidence that the theoretical O(n2) attention complexity translates into measurable performance walls. This work establishes new benchmarking methodologies for transformer evaluation and provides critical insights for practical deployment decisions in production environments.
| Comments: | 8 pages, accepted at IEEE BigData 2025 |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | I.2.7; I.2.6 |
| Cite as: | arXiv:2605.15413 [cs.LG] |
| (or arXiv:2605.15413v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15413 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1109/BigData66926.2025.11401965
DOI(s) linking to related resources |
From: Mahdi Naser Moghadasi [view email]
[v1]
Thu, 14 May 2026 20:57:15 UTC (17 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。