Giacomo Brunetta, Varuni Sastry 0001, Xingfu Wu, Valerie Taylor 0001, Michael E. Papka, Zhiling Lan. Beyond Throughput: Performance and Energy Insights of LLM Inference Across AI Accelerators. In IEEE International Parallel and Distributed Processing Symposium, IPDPS 2026, New Orleans, LA, USA, May 25-29, 2026. pages 970-982, IEEE, 2026. [doi]
@inproceedings{BrunettaSWTPL26,
title = {Beyond Throughput: Performance and Energy Insights of LLM Inference Across AI Accelerators},
author = {Giacomo Brunetta and Varuni Sastry 0001 and Xingfu Wu and Valerie Taylor 0001 and Michael E. Papka and Zhiling Lan},
year = {2026},
doi = {10.1109/IPDPS65963.2026.00083},
url = {https://doi.org/10.1109/IPDPS65963.2026.00083},
researchr = {https://researchr.org/publication/BrunettaSWTPL26},
cites = {0},
citedby = {0},
pages = {970-982},
booktitle = {IEEE International Parallel and Distributed Processing Symposium, IPDPS 2026, New Orleans, LA, USA, May 25-29, 2026},
publisher = {IEEE},
isbn = {979-8-3195-0602-3},
}