Transferable Latency Prediction for LLM Screening in Mobile Immersive Deployment
Open Access
- 26 October 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 28-34
Abstract
No abstract availableFunding Information
- Army Research Laboratory (W911NF-23-2-0224)
This publication has 14 references indexed in Scilit:
- GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices2025
- Large Language Models on Mobile Devices: Measurements, Analysis, and Insights2024
- Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices2023
- Poster: Real-Time Object Substitution for Mobile Diminished Reality with Edge Computing2023
- Efficient Memory Management for Large Language Model Serving with PagedAttention2023
- nn-Meter2021
- An empirical study of latency in an emerging class of edge computing applications for wearable cognitive assistance2017
- MCDNN2016
- DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices2016
- Towards wearable cognitive assistance2014