Download pdf
LLMs at home? An evaluation on the feasibility of popularising On-device-ANI capable hardware in consumer grade devices
- 1 Wesley College Melbourne
* Author to whom correspondence should be addressed.
Abstract
Artificial Narrow Intelligences (ANI) are rapidly becoming an integral part of everyday consumer technology. With products like ChatGPT, Midjourney, and Stable Diffusion gaining widespread popularity, the demand for local hosting of neural networks has significantly increased. However, the typical 'always-online' nature of these services presents several limitations, including dependence on reliable internet connections, privacy concerns, and ongoing operational costs. This essay will explore potential hardware solutions to popularize on-device inferencing of ANI on consumer hardware and speculate on the future of the industry.
Keywords
ANI, neural network, LLM, AI Accelerator, chip design, component efficiency, consumer applications
[1]. Mökander, J., Sheth, M., Watson, D. S., & Floridi, L. (2023). The switch, the ladder, and the matrix: Models for classifying AI systems. Minds and Machines, 33(1), 221–248. https://doi.org/10.1007/s1102302209620y
[2]. Backlinko Team. (2024, June 4). ChatGPT statistics 2024: How many people use ChatGPT? Backlinko. https://backlinko.com/chatgpt-stats
[3]. Zhang, M. (2023, January 26). ChatGPT and OpenAI’s use of Azure’s cloud infrastructure. Dgtl Infra. https://dgtlinfra.com/chatgpt-openai-azure-cloud/
[4]. Ham, M., Woo, S., Jung, J., Song, W., Jang, G., Ahn, Y., & Ahn, H. J. (2022, January 16). Toward among-device AI from on-device AI with stream pipelines. ArXiv.org. https://doi.org/10.48550/arXiv.2201.06026
[5]. Moon, J. J., Lee, H. S., Chu, J., Park, D., Hong, S., Seo, H., Jeong, D., Kong, S., & Ham, M. (2024, January 4). A new frontier of AI: On-device AI training and personalization. ArXiv.org. https://doi.org/10.48550/arXiv.2206.04688
[6]. Schreiner, M. (2023, July 11). GPT-4 architecture, datasets, costs and more leaked. THE DECODER. https://the-decoder.com/gpt-4-architecture-datasets-costs-and-more-leaked/
[7]. Intel. (2024). CPU vs. GPU: What’s the difference? Intel. https://www.intel.com/content/www/us/en/products/docs/processors/cpu-vs-gpu.html
[8]. Amazon Web Services, Inc. (2024). GPU vs CPU - Difference between processing units. Amazon Web Services, Inc. https://aws.amazon.com/compare/the-difference-between-gpus-cpus/
[9]. Frankenfield, J. (2021, September 7). Graphics processing unit (GPU). Investopedia. https://www.investopedia.com/terms/g/graphics-processing-unit-gpu.asp
[10]. Steam. (2024, June). Steam hardware & software survey. Steampowered.com. https://store.steampowered.com/hwsurvey/Steam-Hardware-Software-Survey
[11]. Peru, G. (2023, December 27). What is an NPU? Here’s why everyone’s talking about them. Digital Trends. https://www.digitaltrends.com/computing/what-is-npu/
[12]. Xu, D., Zhang, H., Yang, L., Liu, R., Huang, G., Xu, M., & Liu, X. (2024, July 8). Empowering 1000 tokens/second on-device LLM prefilling with mllm-NPU. ArXiv.org. https://doi.org/10.48550/arXiv.2407.05858
[13]. Microsoft. (2024). All about neural processing units (NPUs) - Microsoft Support. Support.microsoft.com. https://support.microsoft.com/en-au/windows/all-about-neural-processing-units-npus-e77a5637-7705-4915-96c8-0c6a975f9db4
[14]. Li, Q., Zuo, D., Feng, Y., & Wen, D. (2024). Research on high-performance Fourier transform algorithms based on the NPU. Applied Sciences, 14(1), 405. https://doi.org/10.3390/app14010405
[15]. Daimagister. (2024). Are NPUs the key to disrupting Nvidia’s AI dominance? | Resources. DAI Magister. https://www.daimagister.com/resources/npu/
[16]. Al Bawaba. (2024). Apple goes against the AI tide, developing on-device large language model. https://www.proquest.com/newspapers/apple-goes-against-ai-tide-developing-on-device/docview/3043117121/se-2?accountid=6387
Cite this article
Wang,Y. (2024). LLMs at home? An evaluation on the feasibility of popularising On-device-ANI capable hardware in consumer grade devices. Advances in Engineering Innovation,10,26-29.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Journal：Advances in Engineering Innovation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).