The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited affordable access and poses a pressing need for efficiency approaches geared towards high throughput and performance. Multi-input multi-output (MIMO) algorithms such as data multiplexing, offer a promising solution with a many-fold increase in throughput by performing inference for multiple inputs at the cost of a single input. Yet these approaches are not currently performant enough to be deployed in modern systems. We change that by developing MUX-PLMs, a class of high throughput pre-trained language models (PLMs) trained with data multiplexing, that can be fine-tuned for any downstream task to yield high-throughput high-performance. Our novel multiplexing and demultiplexing modules proficiently entangle and disentangle inputs, and enable high-performance high throughput \muxplms{} that are competitive with vanilla PLMs while achieving 2x/5x inference speedup with only a 1−4% drop on a broad suite of tasks.
@article{arxiv.2302.12441,
title = {MUX-PLMs: Data Multiplexing for High-throughput Language Models},
author = {Vishvak Murahari and Ameet Deshpande and Carlos E. Jimenez and Izhak Shafran and Mingqiu Wang and Yuan Cao and Karthik Narasimhan},
journal= {arXiv preprint arXiv:2302.12441},
year = {2023}
}