# CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems

arXiv: https://arxiv.org/abs/2508.11287 · HTML: https://mlsanity.com/paper/2508.11287/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Playing Lottery Tickets with Vision and Language](https://mlsanity.com/paper/2104.11832/) (2021)
- [Zero Bubble Pipeline Parallelism](https://mlsanity.com/paper/2401.10241/) (2023)
- [PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference](https://mlsanity.com/paper/2405.14430/) (2024)
- [WDMoE: Wireless Distributed Large Language Models with Mixture of Experts](https://mlsanity.com/paper/2405.03131/) (2024)
- [GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism](https://mlsanity.com/paper/2406.17145/) (2024)

## Built on by (most cited first, 2 of 2)

- [CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference](https://mlsanity.com/paper/2605.12001/) (2026)
- [Breaking the Ice: Analyzing Cold Start Latency in vLLM](https://mlsanity.com/paper/2606.07362/) (2026)

## Abstract (arXiv)

While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches often ignore the cold-start latency caused by on-demand model loading. In this paper, we propose a latency-aware scheduling framework that overlaps model loading with computation and communication to minimize total inference latency. Based on device and model parameters, the framework dynamically adjusts layer partitioning and allocation to effectively hide loading time, thereby eliminating as many idle periods as possible. We formulate the problem as a Mixed-Integer Non-Linear Program and design an efficient dynamic programming algorithm to optimize model partitioning and device assignment. Experimental results show that the proposed method significantly reduces cold-start latency compared to baseline strategies.