Key points are not available for this paper at this time.
In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchronous overlap for LLMs to mitigate I/O bottlenecks. Our experiments demonstrate a substantial improvement in inference speed, surpassing state-of-the-art methods by over 317% at most.
Building similarity graph...
Analyzing shared references across papers
Loading...
Zhao et al. (Sat,) studied this question.
synapsesocial.com/papers/68e76046b6db6435876d712f — DOI: https://doi.org/10.48550/arxiv.2403.01164
Xuanlei Zhao
Bin Jia
Southwest University of Science and Technology
Haotian Zhou
Shaanxi Science and Technology Department
Building similarity graph...
Analyzing shared references across papers
Loading...