LaTune: Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices.

@inproceedings{zhong-2026-latune, author = {Siqi Zhong and Mugeng Liu and Haiyang Shen and Chongyang Pan and Yun Ma}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{LaTune: Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {5404--5414}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792382}, doi = {https://doi.org/10.1145/3774904.3792382} }