# Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing

arXiv: https://arxiv.org/abs/2511.04002 · HTML: https://mlsanity.com/paper/2511.04002/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models](https://mlsanity.com/paper/2304.01852/) (2023)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities](https://mlsanity.com/paper/2309.16739/) (2023)
- [Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis](https://mlsanity.com/paper/2311.12275/) (2023)
- [Dynamic Split Computing for Efficient Deep Edge Intelligence](https://mlsanity.com/paper/2205.11269/) (2022)
- [Communication-Efficient Split Learning via Adaptive Feature-Wise Compression](https://mlsanity.com/paper/2307.10805/) (2023)
- [Lightweight compression of neural network feature tensors for collaborative intelligence](https://mlsanity.com/paper/2105.06002/) (2021)
- [SplitEE: Early Exit in Deep Neural Networks with Split Computing](https://mlsanity.com/paper/2309.09195/) (2023)
- [Lambda-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI](https://mlsanity.com/paper/2310.14651/) (2023)
- [Predicting the Output Structure of Sparse Matrix Multiplication with Sampled Compression Ratio](https://mlsanity.com/paper/2207.13848/) (2022)
- [Accounting statement analysis at industry level. A gentle introduction to the compositional approach](https://mlsanity.com/paper/2305.16842/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference](https://mlsanity.com/paper/2603.19133/) (2026)
- [Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Networks](https://mlsanity.com/paper/2602.16760/) (2026)
- [Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges](https://mlsanity.com/paper/2609.04778/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and memory-intensive autoregressive decoding. While split computing offers a promising solution by partitioning model execution between edge devices and cloud servers, existing approaches fail to address the unique challenges of autoregressive inference, particularly the iterative token generation process and expanding key-value (KV) cache requirements. This work introduces the first autoregressive-aware split computing framework designed explicitly for LLM deployment on edge devices. Our approach makes three key contributions. First, we develop one-point split compression (OPSC), a mixed-precision quantization scheme that prevents out-of-memory failures by strategically partitioning models into front-end and back-end segments with different precision levels. Second, we propose a two-stage intermediate compression pipeline that combines threshold splitting (TS) and token-wise adaptive bit quantization (TAB-Q) to preserve accuracy-critical activations while dramatically reducing communication overhead. Third, we formulate a unified optimization framework that jointly selects optimal split points, quantization settings, and sequence lengths to satisfy strict memory and latency constraints. Extensive evaluations across diverse LLMs and hardware platforms demonstrate superior performance compared to state-of-the-art quantization methods, including SmoothQuant, OmniQuant, and Atom. The framework achieves a 1.49 inference speedup and significant communication overhead reduction while maintaining or improving model accuracy.