Preprint · 2026 · Open access

Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

Yi Li, Chen Li, Yixuan Chen, Yi Li

arXiv (Cornell University) · Published 14 July 2026 · DOI 10.48550/arxiv.2607.13093

Open PDFView at the publisherCite this paper

In brief

“Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models” is a 2026 preprint by Yi Li and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2026 (2)
References
31
Authors
4

Abstract

On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management, token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply language-adaptive masking and sample target tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-token latency by up to 46.1\% and downlink payloads by up to 67.4\% over baseline split inference, retaining comparable performance to full cloud inference.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, Y., Li, C., Chen, Y., & Li, Y. (2026). Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.13093

MLA 9

Li, Yi, et al. “Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2607.13093.

Chicago

Li, Yi, Chen Li, Yixuan Chen, and Yi Li. 2026. “Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.13093.

Harvard

Li, Y. et al. (2026) ‘Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2607.13093.

IEEE

Y. Li, C. Li, Y. Chen, and Y. Li, “Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2607.13093.

BibTeX

@misc{li2026efficient,
  title     = {{Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models}},
  author    = {Li, Yi and Li, Chen and Chen, Yixuan and Li, Yi},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2607.13093},
  url       = {https://doi.org/10.48550/arxiv.2607.13093}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing

  • large language models
  • on-device inference
  • privacy-preserving inference
  • speculative decoding
  • data quantization
  • streaming inference
  • heterogeneous devices
  • latency reduction

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, Y., Li, C., Chen, Y., & Li, Y. (2026). Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.13093

How many times has this paper been cited?

2 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yi Li, Chen Li, Yixuan Chen, Yi Li.

What is the DOI of this paper?

10.48550/arxiv.2607.13093, permanently at https://doi.org/10.48550/arxiv.2607.13093. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.